K. Madhava Krishna

Tushar Choudhary, Vikrant Dewangan, Shivam Chandhok et al. · mit

Talk2BEV is a large vision-language model (LVLM) interface for bird's-eye view (BEV) maps in autonomous driving contexts. While existing perception systems for autonomous driving scenarios have largely focused on a pre-defined (closed) set of object categories and driving scenarios, Talk2BEV blends recent advances in general-purpose language and vision models with BEV-structured map representations, eliminating the need for task-specific models. This enables a single system to cater to a variety of autonomous driving tasks encompassing visual and spatial reasoning, predicting the intents of traffic actors, and decision-making based on visual cues. We extensively evaluate Talk2BEV on a large number of scene understanding tasks that rely on both the ability to interpret free-form natural language queries, and in grounding these queries to the visual context embedded into the language-enhanced BEV map. To enable further research in LVLMs for autonomous driving scenarios, we develop and release Talk2BEV-Bench, a benchmark encompassing 1000 human-annotated BEV scenarios, with more than 20,000 questions and ground-truth responses from the NuScenes dataset.

Kanishk Jain, Varun Chhangani, Amogh Tiwari et al.

We investigate the Vision-and-Language Navigation (VLN) problem in the context of autonomous driving in outdoor settings. We solve the problem by explicitly grounding the navigable regions corresponding to the textual command. At each timestamp, the model predicts a segmentation mask corresponding to the intermediate or the final navigable region. Our work contrasts with existing efforts in VLN, which pose this task as a node selection problem, given a discrete connected graph corresponding to the environment. We do not assume the availability of such a discretised map. Our work moves towards continuity in action space, provides interpretability through visual feedback and allows VLN on commands requiring finer manoeuvres like "park between the two cars". Furthermore, we propose a novel meta-dataset CARLA-NAV to allow efficient training and validation. The dataset comprises pre-recorded training sequences and a live environment for validation and testing. We provide extensive qualitative and quantitive empirical results to validate the efficacy of the proposed approach.

Abhishek Peri, Kinal Mehta, Avneesh Mishra et al.

Sparse local feature matching is pivotal for many computer vision and robotics tasks. To improve their invariance to challenging appearance conditions and viewing angles, and hence their usefulness, existing learning-based methods have primarily focused on data augmentation-based training. In this work, we propose an alternative, complementary approach that centers on inducing bias in the model architecture itself to generate `rotation-specific' features using Steerable E2-CNNs, that are then group-pooled to achieve rotation-invariant local features. We demonstrate that this high performance, rotation-specific coverage from the steerable CNNs can be expanded to all rotation angles by combining it with augmentation-trained standard CNNs which have broader coverage but are often inaccurate, thus creating a state-of-the-art rotation-robust local feature matcher. We benchmark our proposed methods against existing techniques on HPatches and a newly proposed UrbanScenes3D-Air dataset for visual place recognition. Furthermore, we present a detailed analysis of the performance effects of ensembling, robust estimation, network architecture variations, and the use of rotation priors.

Pranjali Pathre, Anurag Sahu, Ashwin Rao et al.

In this paper, we propose and showcase, for the first time, monocular multi-view layout estimation for warehouse racks and shelves. Unlike typical layout estimation methods, MVRackLay estimates multi-layered layouts, wherein each layer corresponds to the layout of a shelf within a rack. Given a sequence of images of a warehouse scene, a dual-headed Convolutional-LSTM architecture outputs segmented racks, the front and the top view layout of each shelf within a rack. With minimal effort, such an output is transformed into a 3D rendering of all racks, shelves and objects on the shelves, giving an accurate 3D depiction of the entire warehouse scene in terms of racks, shelves and the number of objects on each shelf. MVRackLay generalizes to a diverse set of warehouse scenes with varying number of objects on each shelf, number of shelves and in the presence of other such racks in the background. Further, MVRackLay shows superior performance vis-a-vis its single view counterpart, RackLay, in layout accuracy, quantized in terms of the mean IoU and mAP metrics. We also showcase a multi-view stitching of the 3D layouts resulting in a representation of the warehouse scene with respect to a global reference frame akin to a rendering of the scene from a SLAM pipeline. To the best of our knowledge, this is the first such work to portray a 3D rendering of a warehouse scene in terms of its semantic components - Racks, Shelves and Objects - all from a single monocular camera.

Kushagra Srivastava, Dhruv Patel, Aditya Kumar Jha et al.

Unmanned Aerial Vehicle (UAV) based remote sensing system incorporated with computer vision has demonstrated potential for assisting building construction and in disaster management like damage assessment during earthquakes. The vulnerability of a building to earthquake can be assessed through inspection that takes into account the expected damage progression of the associated component and the component's contribution to structural system performance. Most of these inspections are done manually, leading to high utilization of manpower, time, and cost. This paper proposes a methodology to automate these inspections through UAV-based image data collection and a software library for post-processing that helps in estimating the seismic structural parameters. The key parameters considered here are the distances between adjacent buildings, building plan-shape, building plan area, objects on the rooftop and rooftop layout. The accuracy of the proposed methodology in estimating the above-mentioned parameters is verified through field measurements taken using a distance measuring sensor and also from the data obtained through Google Earth. Additional details and code can be accessed from https://uvrsabi.github.io/ .

Dhruv Patel, Shivani Chepuri, Sarvesh Thakur et al.

Despite the technological advancements in the construction and surveying sector, the inspection of salient features like windows in an under-construction or existing building is predominantly a manual process. Moreover, the number of windows present in a building is directly related to the magnitude of deformation it suffers under earthquakes. In this research, a method to accurately detect and count the number of windows of a building by deploying an Unmanned Aerial Vehicle (UAV) based remote sensing system is proposed. The proposed two-stage method automates the identification and counting of windows by developing computer vision pipelines that utilize data from UAV's onboard camera and other sensors. Quantitative and Qualitative results show the effectiveness of our proposed approach in accurately detecting and counting the windows compared to the existing method.

Antareep Singha, Laksh Nanwani, Mathai Mathew P. et al.

Safe and computationally efficient local planning for mobile robots in dense, unstructured human crowds remains a fundamental challenge. Moreover, ensuring that robot trajectories are similar to how a human moves will increase the acceptance of the robot in human environments. In this paper, we present Crowd-FM, a learning-based approach to address both safety and human-likeness challenges. Our approach has two novel components. First, we train a Conditional Flow-Matching (CFM) policy over a dataset of optimally controlled trajectories to learn a set of collision-free primitives that a robot can choose at any given scenario. The chosen optimal control solver can generate multi-modal collision-free trajectories, allowing the CFM policy to learn a diverse set of maneuvers. Secondly, we learn a score function over a dataset of human demonstration trajectories that provides a human-likeness score for the flow primitives. At inference time, computing the optimal trajectory requires selecting the one with the highest score. Our approach improves the state-of-the-art by showing that our CFM policy alone can produce collision-free navigation with a higher success rate than existing learning-based baselines. Furthermore, when augmented with inference-time refinement, our approach can outperform even expensive optimisation-based planning approaches. Finally, we validate that our scoring network can select trajectories closer to the expert data than a manually designed cost function.

Simon Idoko, B. Bhanu Teja, K. Madhava Krishna et al.

Coordination behavior in robot swarms is inherently multi-modal in nature. That is, there are numerous ways in which a swarm of robots can avoid inter-agent collisions and reach their respective goals. However, the problem of generating diverse and feasible swarm behaviors in a scalable manner remains largely unaddressed. In this paper, we fill this gap by combining generative models with a safety-filter (SF). Specifically, we sample diverse trajectories from a learned generative model which is subsequently projected onto the feasible set using the SF. We experiment with two choices for generative models, namely: Conditional Variational Autoencoder (CVAE) and Vector-Quantized Variational Autoencoder (VQ-VAE). We highlight the trade-offs these two models provide in terms of computation time and trajectory diversity. We develop a custom solver for our SF and equip it with a neural network that predicts context-specific initialization. Thecinitialization network is trained in a self-supervised manner, taking advantage of the differentiability of the SF solver. We provide two sets of empirical results. First, we demonstrate that we can generate a large set of multi-modal, feasible trajectories, simulating diverse swarm behaviors, within a few tens of milliseconds. Second, we show that our initialization network provides faster convergence of our SF solver vis-a-vis other alternative heuristics.

Laksh Nanwani, Kumaraditya Gupta, Aditya Mathur et al.

Humans excel at forming mental maps of their surroundings, equipping them to understand object relationships and navigate based on language queries. Our previous work, SI Maps (Nanwani L, Agarwal A, Jain K, et al. Instance-level semantic maps for vision language navigation. In: 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). IEEE; 2023 Aug.), showed that having instance-level information and the semantic understanding of an environment helps significantly improve performance for language-guided tasks. We extend this instance-level approach to 3D while increasing the pipeline's robustness and improving quantitative and qualitative results. Our method leverages foundational models for object recognition, image segmentation, and feature extraction. We propose a representation that results in a 3D point cloud map with instance-level embeddings, which bring in the semantic understanding that natural language commands can query. Quantitatively, the work improves upon the success rate of language-guided tasks. At the same time, we qualitatively observe the ability to identify instances more clearly and leverage the foundational models and language and image-aligned embeddings to identify objects that, otherwise, a closed-set approach wouldn't be able to identify. Project Page - https://smart-wheelchair-rrc.github.io/o3d-sim-webpage

Keshav Gupta, Tejas S. Stanley, Pranjal Paul et al.

Drivable Free-space prediction is a fundamental and crucial problem in autonomous driving. Recent works have addressed the problem by representing the entire non-obstacle road regions as the free-space. In contrast our aim is to estimate the driving corridors that are a navigable subset of the entire road region. Unfortunately, existing corridor estimation methods directly assume a BEV-centric representation, which is hard to obtain. In contrast, we frame drivable free-space corridor prediction as a pure image perception task, using only monocular camera input. However such a formulation poses several challenges as one doesn't have the corresponding data for such free-space corridor segments in the image. Consequently, we develop a novel self-supervised approach for free-space sample generation by leveraging future ego trajectories and front-view camera images, making the process of visual corridor estimation dependent on the ego trajectory. We then employ a diffusion process to model the distribution of such segments in the image. However, the existing binary mask-based representation for a segment poses many limitations. Therefore, we introduce ContourDiff, a specialized diffusion-based architecture that denoises over contour points rather than relying on binary mask representations, enabling structured and interpretable free-space predictions. We evaluate our approach qualitatively and quantitatively on both nuScenes and CARLA, demonstrating its effectiveness in accurately predicting safe multimodal navigable corridors in the image.

Unni Krishnan R Nair, Anish Gupta, D. A. Sasi Kiran et al.

We consider the problem of an agent/robot with non-holonomic kinematics avoiding many dynamic obstacles. State and velocity noise of both the robot and obstacles as well as the robot's control noise are modelled as non-parametric distributions as often the Gaussian assumptions of noise models are violated in real-world scenarios. Under these assumptions, we formulate a robust MPC that samples robotic controls effectively in a manner that aligns the robot to the goal state while avoiding obstacles under the duress of such non-parametric noise. In particular, the MPC incorporates a distribution matching cost that effectively aligns the distribution of the current collision cone to a certain desired distribution whose samples are collision-free. This cost is posed as a distance function in the Hilbert Space, whose minimization typically results in the collision cone samples becoming collision-free. We compare and show tangible performance gain with methods that model the collision cone distribution by linearizing the Gaussian approximations of the original non-parametric state and obstacle distributions. We also show superior performance with methods that pose a chance constraint formulation of the Gaussian approximations of non-parametric noise without subjecting such approximations to further linearizations. The performance gain is shown both in terms of trajectory length and control costs that vindicates the efficacy of the proposed method. To the best of our knowledge, this is the first presentation of non-holonomic collision avoidance of moving obstacles in the presence of non-parametric state, velocity and actuator noise models.

Mohd Omama, Sundar Sripada V. S., Sandeep Chinchali et al.

We embark on a hitherto unreported problem of an autonomous robot (self-driving car) navigating in dynamic scenes in a manner that reduces its localization error and eventual cumulative drift or Absolute Trajectory Error, which is pronounced in such dynamic scenes. With the hugely popular Velodyne-16 3D LIDAR as the main sensing modality, and the accurate LIDAR-based Localization and Mapping algorithm, LOAM, as the state estimation framework, we show that in the absence of a navigation policy, drift rapidly accumulates in the presence of moving objects. To overcome this, we learn actions that lead to drift-minimized navigation through a suitable set of reward and penalty functions. We use Proximal Policy Optimization, a class of Deep Reinforcement Learning methods, to learn the actions that result in drift-minimized trajectories. We show by extensive comparisons on a variety of synthetic, yet photo-realistic scenes made available through the CARLA Simulator the superior performance of the proposed framework vis-a-vis methods that do not adopt such policies.

Kaustubh Mani, N. Sai Shankar, Krishna Murthy Jatavallabhula et al.

Given an image or a video captured from a monocular camera, amodal layout estimation is the task of predicting semantics and occupancy in bird's eye view. The term amodal implies we also reason about entities in the scene that are occluded or truncated in image space. While several recent efforts have tackled this problem, there is a lack of standardization in task specification, datasets, and evaluation protocols. We address these gaps with AutoLay, a dataset and benchmark for amodal layout estimation from monocular images. AutoLay encompasses driving imagery from two popular datasets: KITTI and Argoverse. In addition to fine-grained attributes such as lanes, sidewalks, and vehicles, we also provide semantically annotated 3D point clouds. We implement several baselines and bleeding edge approaches, and release our data and code.

Karnik Ram, Chaitanya Kharyal, Sudarshan S. Harithas et al.

Modern visual-inertial navigation systems (VINS) are faced with a critical challenge in real-world deployment: they need to operate reliably and robustly in highly dynamic environments. Current best solutions merely filter dynamic objects as outliers based on the semantics of the object category. Such an approach does not scale as it requires semantic classifiers to encompass all possibly-moving object classes; this is hard to define, let alone deploy. On the other hand, many real-world environments exhibit strong structural regularities in the form of planes such as walls and ground surfaces, which are also crucially static. We present RP-VIO, a monocular visual-inertial odometry system that leverages the simple geometry of these planes for improved robustness and accuracy in challenging dynamic environments. Since existing datasets have a limited number of dynamic elements, we also present a highly-dynamic, photorealistic synthetic dataset for a more effective evaluation of the capabilities of modern VINS systems. We evaluate our approach on this dataset, and three diverse sequences from standard datasets including two real-world dynamic sequences and show a significant improvement in robustness and accuracy over a state-of-the-art monocular visual-inertial odometry system. We also show in simulation an improvement over a simple dynamic-features masking approach. Our code and dataset are publicly available.

Meher Shashwat Nigam, Avinash Prabhu, Anurag Sahu et al.

Given a monocular colour image of a warehouse rack, we aim to predict the bird's-eye view layout for each shelf in the rack, which we term as multi-layer layout prediction. To this end, we present RackLay, a deep neural network for real-time shelf layout estimation from a single image. Unlike previous layout estimation methods, which provide a single layout for the dominant ground plane alone, RackLay estimates the top-view and front-view layout for each shelf in the considered rack populated with objects. RackLay's architecture and its variants are versatile and estimate accurate layouts for diverse scenes characterized by varying number of visible shelves in an image, large range in shelf occupancy factor and varied background clutter. Given the extreme paucity of datasets in this space and the difficulty involved in acquiring real data from warehouses, we additionally release a flexible synthetic dataset generation pipeline WareSynth which allows users to control the generation process and tailor the dataset according to contingent application. The ablations across architectural variants and comparison with strong prior baselines vindicate the efficacy of RackLay as an apt architecture for the novel problem of multi-layered layout estimation. We also show that fusing the top-view and front-view enables 3D reasoning applications such as metric free space estimation for the considered rack.

Udit Singh Parihar, Aniket Gujarathi, Kinal Mehta et al.

The use of local detectors and descriptors in typical computer vision pipelines work well until variations in viewpoint and appearance change become extreme. Past research in this area has typically focused on one of two approaches to this challenge: the use of projections into spaces more suitable for feature matching under extreme viewpoint changes, and attempting to learn features that are inherently more robust to viewpoint change. In this paper, we present a novel framework that combines learning of invariant descriptors through data augmentation and orthographic viewpoint projection. We propose rotation-robust local descriptors, learnt through training data augmentation based on rotation homographies, and a correspondence ensemble technique that combines vanilla feature correspondences with those obtained through rotation-robust features. Using a range of benchmark datasets as well as contributing a new bespoke dataset for this research domain, we evaluate the effectiveness of the proposed approach on key tasks including pose estimation and visual place recognition. Our system outperforms a range of baseline and state-of-the-art techniques, including enabling higher levels of place recognition precision across opposing place viewpoints and achieves practically-useful performance levels even under extreme viewpoint changes.

Rahul Sajnani, AadilMehdi Sanchawala, Krishna Murthy Jatavallabhula et al.

We present DRACO, a method for Dense Reconstruction And Canonicalization of Object shape from one or more RGB images. Canonical shape reconstruction, estimating 3D object shape in a coordinate space canonicalized for scale, rotation, and translation parameters, is an emerging paradigm that holds promise for a multitude of robotic applications. Prior approaches either rely on painstakingly gathered dense 3D supervision, or produce only sparse canonical representations, limiting real-world applicability. DRACO performs dense canonicalization using only weak supervision in the form of camera poses and semantic keypoints at train time. During inference, DRACO predicts dense object-centric depth maps in a canonical coordinate-space, solely using one or more RGB images of an object. Extensive experiments on canonical shape reconstruction and pose estimation show that DRACO is competitive or superior to fully-supervised methods.

Swapnil Daga, Gokul B. Nair, Anirudha Ramesh et al.

In this paper, we present BirdSLAM, a novel simultaneous localization and mapping (SLAM) system for the challenging scenario of autonomous driving platforms equipped with only a monocular camera. BirdSLAM tackles challenges faced by other monocular SLAM systems (such as scale ambiguity in monocular reconstruction, dynamic object localization, and uncertainty in feature representation) by using an orthographic (bird's-eye) view as the configuration space in which localization and mapping are performed. By assuming only the height of the ego-camera above the ground, BirdSLAM leverages single-view metrology cues to accurately localize the ego-vehicle and all other traffic participants in bird's-eye view. We demonstrate that our system outperforms prior work that uses strictly greater information, and highlight the relevance of each design decision via an ablation analysis.

Shashank Srikanth, Mithun Babu, Houman Masnavi et al.

Joint space trajectory optimization under end-effector task constraints leads to a challenging non-convex problem. Thus, a real-time adaptation of prior computed trajectories to perturbation in task constraints often becomes intractable. Existing works use the so-called warm-starting of trajectory optimization to improve computational performance. We present a fundamentally different approach that relies on deriving analytical gradients of the optimal solution with respect to the task constraint parameters. This gradient map characterizes the direction in which the prior computed joint trajectories need to be deformed to comply with the new task constraints. Subsequently, we develop an iterative line-search algorithm for computing the scale of deformation. Our algorithm provides near real-time adaptation of joint trajectories for a diverse class of task perturbations such as (i) changes in initial and final joint configurations of end-effector orientation-constrained trajectories and (ii) changes in end-effector goal or way-points under end-effector orientation constraints. We relate each of these examples to real-world applications ranging from learning from demonstration to obstacle avoidance. We also show that our algorithm produces trajectories with quality similar to what one would obtain by solving the trajectory optimization from scratch with warm-start initialization. But most importantly, our algorithm achieves a worst-case speed-up of 160x over the latter approach.

Satyajit Tourani, Dhagash Desai, Udit Singh Parihar et al.

Significant advances have been made recently in Visual Place Recognition (VPR), feature correspondence, and localization due to the proliferation of deep-learning-based methods. However, existing approaches tend to address, partially or fully, only one of two key challenges: viewpoint change and perceptual aliasing. In this paper, we present novel research that simultaneously addresses both challenges by combining deep-learned features with geometric transformations based on reasonable domain assumptions about navigation on a ground-plane, whilst also removing the requirement for specialized hardware setup (e.g. lighting, downwards facing cameras). In particular, our integration of VPR with SLAM by leveraging the robustness of deep-learned features and our homography-based extreme viewpoint invariance significantly boosts the performance of VPR, feature correspondence, and pose graph submodules of the SLAM pipeline. For the first time, we demonstrate a localization system capable of state-of-the-art performance despite perceptual aliasing and extreme 180-degree-rotated viewpoint change in a range of real-world and simulated experiments. Our system is able to achieve early loop closures that prevent significant drifts in SLAM trajectories. We also compare extensively several deep architectures for VPR and descriptor matching. We also show that superior place recognition and descriptor matching across opposite views results in a similar performance gain in back-end pose graph optimization.

Nivedita Rufus, Unni Krishnan R Nair, K. Madhava Krishna et al.

In this paper, we present a simple baseline for visual grounding for autonomous driving which outperforms the state of the art methods, while retaining minimal design choices. Our framework minimizes the cross-entropy loss over the cosine distance between multiple image ROI features with a text embedding (representing the give sentence/phrase). We use pre-trained networks for obtaining the initial embeddings and learn a transformation layer on top of the text embedding. We perform experiments on the Talk2Car dataset and achieve 68.7% AP50 accuracy, improving upon the previous state of the art by 8.6%. Our investigation suggests reconsideration towards more approaches employing sophisticated attention mechanisms or multi-stage reasoning or complex metric learning loss functions by showing promise in simpler alternatives.

Mithun. P, Shaunak A. Mehta, Suril V. Shah et al.

Classical Image-Based Visual Servoing (IBVS) makes use of geometric image features like point, straight line and image moments to control a robotic system. Robust extraction and real-time tracking of these features are crucial to the performance of the IBVS. Moreover, such features can be unsuitable for real world applications where it might not be easy to distinguish a target from the rest of the environment. Alternatively, an approach based on complete photometric data can avoid the requirement of feature extraction, tracking and object detection. In this work, we propose one such probabilistic model based approach which uses entire photometric data for the purpose of visual servoing. A novel image modelling method has been proposed using Student Mixture Model (SMM), which is based on Multivariate Student's t-Distribution. Consequently, a vision-based control law is formulated as a least squares minimisation problem. Efficacy of the proposed framework is demonstrated for 2D and 3D positioning tasks showing favourable error convergence and acceptable camera trajectories. Numerical experiments are also carried out to show robustness to distinct image scenes and partial occlusion.

Nivedita Rufus, Unni Krishnan R. Nair, A. V. S. Sai Bhargav Kumar et al.

In this paper, we present SROM, a novel real-time Simultaneous Localization and Mapping (SLAM) system for autonomous vehicles. The keynote of the paper showcases SROM's ability to maintain localization at low sampling rates or at high linear or angular velocities where most popular LiDAR based localization approaches get degraded fast. We also demonstrate SROM to be computationally efficient and capable of handling high-speed maneuvers. It also achieves low drifts without the need for any other sensors like IMU and/or GPS. Our method has a two-layer structure wherein first, an approximate estimate of the rotation angle and translation parameters are calculated using a Phase Only Correlation (POC) method. Next, we use this estimate as an initialization for a point-to-plane ICP algorithm to obtain fine matching and registration. Another key feature of the proposed algorithm is the removal of dynamic objects before matching the scans. This improves the performance of our system as the dynamic objects can corrupt the matching scheme and derail localization. Our SLAM system can build reliable maps at the same time generating high-quality odometry. We exhaustively evaluated the proposed method in many challenging highways/country/urban sequences from the KITTI dataset and the results demonstrate better accuracy in comparisons to other state-of-the-art methods with reduced computational expense aiding in real-time realizations. We have also integrated our SROM system with our in-house autonomous vehicle and compared it with the state-of-the-art methods like LOAM and LeGO-LOAM.

Aniket Pokale, Aditya Aggarwal, K. Madhava Krishna

This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image. Geared towards high fidelity reconstruction, several recent approaches leverage implicit surface representations and deep neural networks to estimate a 3D mesh of an object, given a single image. However, all such approaches recover only the shape of an object; the reconstruction is often in a canonical frame, unsuitable for downstream robotics tasks. To this end, we leverage recent advances in differentiable rendering (in particular, rasterization) to close the loop with 3D reconstruction in camera frame. We demonstrate that our approach---dubbed reconstruct, rasterize and backprop (RRB) achieves significantly lower pose estimation errors compared to prior art, and is able to recover dense object shapes and poses from imagery. We further extend our results to an (offline) setup, where we demonstrate a dense monocular object-centric egomotion estimation system.

Y V S Harish, Harit Pandya, Ayush Gaud et al.

Existing deep learning based visual servoing approaches regress the relative camera pose between a pair of images. Therefore, they require a huge amount of training data and sometimes fine-tuning for adaptation to a novel scene. Furthermore, current approaches do not consider underlying geometry of the scene and rely on direct estimation of camera pose. Thus, inaccuracies in prediction of the camera pose, especially for distant goals, lead to a degradation in the servoing performance. In this paper, we propose a two-fold solution: (i) We consider optical flow as our visual features, which are predicted using a deep neural network. (ii) These flow features are then systematically integrated with depth estimates provided by another neural network using interaction matrix. We further present an extensive benchmark in a photo-realistic 3D simulation across diverse scenes to study the convergence and generalisation of visual servoing approaches. We show convergence for over 3m and 40 degrees while maintaining precise positioning of under 2cm and 1 degree on our challenging benchmark where the existing approaches that are unable to converge for majority of scenarios for over 1.5m and 20 degrees. Furthermore, we also evaluate our approach for a real scenario on an aerial robot. Our approach generalizes to novel scenarios producing precise and robust servoing performance for 6 degrees of freedom positioning tasks with even large camera transformations without any retraining or fine-tuning.

Kaustubh Mani, Swapnil Daga, Shubhika Garg et al.

In this paper, we address the novel, highly challenging problem of estimating the layout of a complex urban driving scenario. Given a single color image captured from a driving platform, we aim to predict the bird's-eye view layout of the road and other traffic participants. The estimated layout should reason beyond what is visible in the image, and compensate for the loss of 3D information due to projection. We dub this problem amodal scene layout estimation, which involves "hallucinating" scene layout for even parts of the world that are occluded in the image. To this end, we present MonoLayout, a deep neural network for real-time amodal scene layout estimation from a single image. We represent scene layout as a multi-channel semantic occupancy grid, and leverage adversarial feature learning to hallucinate plausible completions for occluded image parts. Due to the lack of fair baseline methods, we extend several state-of-the-art approaches for road-layout estimation and vehicle occupancy estimation in bird's-eye view to the amodal setup for rigorous evaluation. By leveraging temporal sensor fusion to generate training labels, we significantly outperform current art over a number of datasets. On the KITTI and Argoverse datasets, we outperform all baselines by a significant margin. We also make all our annotations, and code publicly available. A video abstract of this paper is available https://www.youtube.com/watch?v=HcroGyo6yRQ .

Sai Shubodh Puligilla, Satyajit Tourani, Tushar Vaidya et al.

We showcase a topological mapping framework for a challenging indoor warehouse setting. At the most abstract level, the warehouse is represented as a Topological Graph where the nodes of the graph represent a particular warehouse topological construct (e.g. rackspace, corridor) and the edges denote the existence of a path between two neighbouring nodes or topologies. At the intermediate level, the map is represented as a Manhattan Graph where the nodes and edges are characterized by Manhattan properties and as a Pose Graph at the lower-most level of detail. The topological constructs are learned via a Deep Convolutional Network while the relational properties between topological instances are learnt via a Siamese-style Neural Network. In the paper, we show that maintaining abstractions such as Topological Graph and Manhattan Graph help in recovering an accurate Pose Graph starting from a highly erroneous and unoptimized Pose Graph. We show how this is achieved by embedding topological and Manhattan relations as well as Manhattan Graph aided loop closure relations as constraints in the backend Pose Graph optimization framework. The recovery of near ground-truth Pose Graph on real-world indoor warehouse scenes vindicate the efficacy of the proposed framework.

Gokul B. Nair, Swapnil Daga, Rahul Sajnani et al.

In this paper, we tackle the problem of multibody SLAM from a monocular camera. The term multibody, implies that we track the motion of the camera, as well as that of other dynamic participants in the scene. The quintessential challenge in dynamic scenes is unobservability: it is not possible to unambiguously triangulate a moving object from a moving monocular camera. Existing approaches solve restricted variants of the problem, but the solutions suffer relative scale ambiguity (i.e., a family of infinitely many solutions exist for each pair of motions in the scene). We solve this rather intractable problem by leveraging single-view metrology, advances in deep learning, and category-level shape estimation. We propose a multi pose-graph optimization formulation, to resolve the relative and absolute scale factor ambiguities involved. This optimization helps us reduce the average error in trajectories of multiple bodies over real-world datasets, such as KITTI. To the best of our knowledge, our method is the first practical monocular multi-body SLAM system to perform dynamic multi-object and ego localization in a unified framework in metric scale.

P. S. Naga Jyotish, Bharath Gopalakrishnan, A. V. S. Sai Bhargav Kumar et al.

The probabilistic velocity obstacle (PVO) extends the concept of velocity obstacle (VO) to work in uncertain dynamic environments. In this paper, we show how a robust model predictive control (MPC) with PVO constraints under non-parametric uncertainty can be made computationally tractable. At the core of our formulation is a novel yet simple interpretation of our robust MPC as a problem of matching the distribution of PVO with a certain desired distribution. To this end, we propose two methods. Our first baseline method is based on approximating the distribution of PVO with a Gaussian Mixture Model (GMM) and subsequently performing distribution matching using Kullback Leibler (KL) divergence metric. Our second formulation is based on the possibility of representing arbitrary distributions as functions in Reproducing Kernel Hilbert Space (RKHS). We use this foundation to interpret our robust MPC as a problem of minimizing the distance between the desired distribution and the distribution of the PVO in the RKHS. Both the RKHS and GMM based formulation can work with any uncertainty distribution and thus allowing us to relax the prevalent Gaussian assumption in the existing works. We validate our formulation by taking an example of 2D navigation of quadrotors with a realistic noise model for perception and ego-motion uncertainty. In particular, we present a systematic comparison between the GMM and the RKHS approach and show that while both approaches can produce safe trajectories, the former is highly conservative and leads to poor tracking and control costs. Furthermore, RKHS based approach gives better computational times that are up to one order of magnitude lesser than the computation time of the GMM based approach.

Sriram N. N., Gourav Kumar, Abhay Singh et al.

Autonomous explorative robots frequently encounter scenarios where multiple future trajectories can be pursued. Often these are cases with multiple paths around an obstacle or trajectory options towards various frontiers. Humans in such situations can inherently perceive and reason about the surrounding environment to identify several possibilities of either manoeuvring around the obstacles or moving towards various frontiers. In this work, we propose a 2 stage Convolutional Neural Network architecture which mimics such an ability to map the perceived surroundings to multiple trajectories that a robot can choose to traverse. The first stage is a Trajectory Proposal Network which suggests diverse regions in the environment which can be occupied in the future. The second stage is a Trajectory Sampling network which provides a finegrained trajectory over the regions proposed by Trajectory Proposal Network. We evaluate our framework in diverse and complicated real life settings. For the outdoor case, we use the KITTI dataset and our own outdoor driving dataset. In the indoor setting, we use an autonomous drone to navigate various scenarios and also a ground robot which can explore the environment using the trajectories proposed by our framework. Our experiments suggest that the framework is able to develop a semantic understanding of the obstacles, open regions and identify diverse trajectories that a robot can traverse. Our comparisons portray the performance gain of the proposed architecture over a diverse set of methods against which it is compared.

P. S. Naga Jyotish, Yash Goel, A. V. S. Sai Bhargav Kumar et al.

In this paper, we present "IVO: Inverse Velocity Obstacles" an ego-centric framework that improves the real time implementation. The proposed method stems from the concept of velocity obstacle and can be applied for both single agent and multi-agent system. It focuses on computing collision free maneuvers without any knowledge or assumption on the pose and the velocity of the robot. This is primarily achieved by reformulating the velocity obstacle to adapt to an ego-centric framework. This is a significant step towards improving real time implementations of collision avoidance in dynamic environments as there is no dependency on state estimation techniques to infer the robot pose and velocity. We evaluate IVO for both single agent and multi-agent in different scenarios and show it's efficacy over the existing formulations. We also show the real time scalability of the proposed methodology.

Vignesh Prasad, Karmesh Yadav, Rohitashva Singh Saurabh et al.

Monocular SLAM refers to using a single camera to estimate robot ego motion while building a map of the environment. While Monocular SLAM is a well studied problem, automating Monocular SLAM by integrating it with trajectory planning frameworks is particularly challenging. This paper presents a novel formulation based on Reinforcement Learning (RL) that generates fail safe trajectories wherein the SLAM generated outputs do not deviate largely from their true values. Quintessentially, the RL framework successfully learns the otherwise complex relation between perceptual inputs and motor actions and uses this knowledge to generate trajectories that do not cause failure of SLAM. We show systematically in simulations how the quality of the SLAM dramatically improves when trajectories are computed using RL. Our method scales effectively across Monocular SLAM frameworks in both simulation and in real world experiments with a mobile robot.

Bharath Gopalakrishnan, Arun Kumar Singh, K. Madhava Krishna et al.

In this paper, we present an efficient algorithm for solving a class of chance constrained optimization under non-parametric uncertainty. Our algorithm is built on the possibility of representing arbitrary distributions as functions in Reproducing Kernel Hilbert Space (RKHS). We use this foundation to formulate chance constrained optimization as one of minimizing the distance between a desired distribution and the distribution of the constraint functions in the RKHS. We provide a systematic way of constructing the desired distribution based on a notion of scenario approximation. Furthermore, we use the kernel trick to show that the computational complexity of our reformulated optimization problem is comparable to solving a deterministic variant of the chance-constrained optimization. We validate our formulation on two important robotic/control applications: (i) reactive collision avoidance of mobile robots in uncertain dynamic environments and (ii) inverse dynamics based path tracking of manipulators under perception uncertainty. In both these applications, the underlying chance constraints are defined over highly non-linear and non-convex functions of the uncertain parameters and possibly also decision variables. We also benchmark our formulation with the existing approaches in terms of sample complexity and the achieved optimal cost highlighting significant improvements in both these metrics.

Meha Kaushik, Phaniteja S, K. Madhava Krishna

Multi-agent learning provides a potential framework for learning and simulating traffic behaviors. This paper proposes a novel architecture to learn multiple driving behaviors in a traffic scenario. The proposed architecture can learn multiple behaviors independently as well as simultaneously. We take advantage of the homogeneity of agents and learn in a parameter sharing paradigm. To further speed up the training process asynchronous updates are employed into the architecture. While learning different behaviors simultaneously, the given framework was also able to learn cooperation between the agents, without any explicit communication. We applied this framework to learn two important behaviors in driving: 1) Lane-Keeping and 2) Over-Taking. Results indicate faster convergence and learning of a more generic behavior, that is scalable to any number of agents. When compared the results with existing approaches, our results indicate equal and even better performance in some cases.

Adarsh Modh, Siddharth Singh, A. V. S. Sai Bhargav Kumar et al.

In this paper, we present a novel control law for longitudinal speed control of autonomous vehicles. The key contributions of the proposed work include the design of a control law that reactively integrates the longitudinal surface gradient of road into its operation. In contrast to the existing works, we found that integrating the path gradient into the control framework improves the speed tracking efficacy. Since the control law is implemented over a shrinking domain scheme, it minimizes the integrated error by recomputing the control inputs at every discretized step and consequently provides less reaction time. This makes our control law suitable for motion planning frameworks that are operating at high frequencies. Furthermore, our work is implemented using a generalized vehicle model and can be easily extended to other classes of vehicles. The performance of gradient aware-shrinking domain based controller is implemented and tested on a stock electric vehicle on which a number of sensors are mounted. Results from the tests show the robustness of our control law for speed tracking on a terrain with varying gradient while also considering stringent time constraints imposed by the planning framework.

Ganesh Iyer, J. Krishna Murthy, Gunshi Gupta et al.

With the success of deep learning based approaches in tackling challenging problems in computer vision, a wide range of deep architectures have recently been proposed for the task of visual odometry (VO) estimation. Most of these proposed solutions rely on supervision, which requires the acquisition of precise ground-truth camera pose information, collected using expensive motion capture systems or high-precision IMU/GPS sensor rigs. In this work, we propose an unsupervised paradigm for deep visual odometry learning. We show that using a noisy teacher, which could be a standard VO pipeline, and by designing a loss term that enforces geometric consistency of the trajectory, we can train accurate deep models for VO that do not require ground-truth labels. We leverage geometry as a self-supervisory signal and propose "Composite Transformation Constraints (CTCs)", that automatically generate supervisory signals for training and enforce geometric consistency in the VO estimate. We also present a method of characterizing the uncertainty in VO estimates thus obtained. To evaluate our VO pipeline, we present exhaustive ablation studies that demonstrate the efficacy of end-to-end, self-supervised methodologies to train deep models for monocular VO. We show that leveraging concepts from geometry and incorporating them into the training of a recurrent neural network results in performance competitive to supervised deep VO methods.

Ganesh Iyer, R. Karnik Ram., J. Krishna Murthy et al.

3D LiDARs and 2D cameras are increasingly being used alongside each other in sensor rigs for perception tasks. Before these sensors can be used to gather meaningful data, however, their extrinsics (and intrinsics) need to be accurately calibrated, as the performance of the sensor rig is extremely sensitive to these calibration parameters. A vast majority of existing calibration techniques require significant amounts of data and/or calibration targets and human effort, severely impacting their applicability in large-scale production systems. We address this gap with CalibNet: a self-supervised deep network capable of automatically estimating the 6-DoF rigid body transformation between a 3D LiDAR and a 2D camera in real-time. CalibNet alleviates the need for calibration targets, thereby resulting in significant savings in calibration efforts. During training, the network only takes as input a LiDAR point cloud, the corresponding monocular image, and the camera calibration matrix K. At train time, we do not impose direct supervision (i.e., we do not directly regress to the calibration parameters, for example). Instead, we train the network to predict calibration parameters that maximize the geometric and photometric consistency of the input images and point clouds. CalibNet learns to iteratively solve the underlying geometric problem and accurately predicts extrinsic calibration parameters for a wide range of mis-calibrations, without requiring retraining or domain adaptation. The project page is hosted at https://epiception.github.io/CalibNet

Krishnam Gupta, Syed Ashar Javed, Vineet Gandhi et al.

We present here, a novel network architecture called MergeNet for discovering small obstacles for on-road scenes in the context of autonomous driving. The basis of the architecture rests on the central consideration of training with less amount of data since the physical setup and the annotation process for small obstacles is hard to scale. For making effective use of the limited data, we propose a multi-stage training procedure involving weight-sharing, separate learning of low and high level features from the RGBD input and a refining stage which learns to fuse the obtained complementary features. The model is trained and evaluated on the Lost and Found dataset and is able to achieve state-of-art results with just 135 images in comparison to the 1000 images used by the previous benchmark. Additionally, we also compare our results with recent methods trained on 6000 images and show that our method achieves comparable performance with only 1000 training samples.

Mithun Babu, Raghu Ram Theerthala, Arun Kumar Singh et al.

In this paper, we propose a new model predictive control (MPC) formulation for autonomous driving. The novelty of our MPC stems from the following results. Firstly, we adopt an alternating minimization approach wherein linear velocities and angular accelerations are alternately optimized. We show that in contrast to the joint optimization, the alternating minimization exploits the structure of the problem better, which in turn translates to reduction in computation time. Secondly, our MPC explicitly incorporates the time dependent non-linear actuator dynamics that captures the transient response of the vehicle for a given commanded velocity. This added complexity improves the predictive component of MPC resulting in improved margin of inter-vehicle distance during maneuvers like overtaking, lane-change, etc. Although, past works have also incorporated actuator dynamics within MPC, there has been very few attempts towards coupling actuator dynamics to collision avoidance constraints through the non-holonomic motion model of the vehicle and analyzing the resulting behavior. We use a high fidelity simulator to benchmark our actuator dynamics augmented MPC with other related approaches in terms of metrics like inter-vehicle distance, trajectory smoothness, and velocity overshoot.

Junaid Ahmed Ansari, Sarthak Sharma, Anshuman Majumdar et al.

Accurate localization of other traffic participants is a vital task in autonomous driving systems. State-of-the-art systems employ a combination of sensing modalities such as RGB cameras and LiDARs for localizing traffic participants, but most such demonstrations have been confined to plain roads. We demonstrate, to the best of our knowledge, the first results for monocular object localization and shape estimation on surfaces that do not share the same plane with the moving monocular camera. We approximate road surfaces by local planar patches and use semantic cues from vehicles in the scene to initialize a local bundle-adjustment like procedure that simultaneously estimates the pose and shape of the vehicles, and the orientation of the local ground plane on which the vehicle stands as well. We evaluate the proposed approach on the KITTI and SYNTHIA-SF benchmarks, for a variety of road plane configurations. The proposed approach significantly improves the state-of-the-art for monocular object localization on arbitrarily-shaped roads.

Sarthak Sharma, Junaid Ahmed Ansari, J. Krishna Murthy et al.

This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios. Using images from a monocular camera alone, we devise pairwise costs for object tracks, based on several 3D cues such as object pose, shape, and motion. The proposed costs are agnostic to the data association method and can be incorporated into any optimization framework to output the pairwise data associations. These costs are easy to implement, can be computed in real-time, and complement each other to account for possible errors in a tracking-by-detection framework. We perform an extensive analysis of the designed costs and empirically demonstrate consistent improvement over the state-of-the-art under varying conditions that employ a range of object detectors, exhibit a variety in camera and object motions, and, more importantly, are not reliant on the choice of the association framework. We also show that, by using the simplest of associations frameworks (two-frame Hungarian assignment), we surpass the state-of-the-art in multi-object-tracking on road scenes. More qualitative and quantitative results can be found at the following URL: https://junaidcs032.github.io/Geometry_ObjectShape_MOT/.

Parv Parkhiya, Rishabh Khawad, J. Krishna Murthy et al.

We present a new paradigm for real-time object-oriented SLAM with a monocular camera. Contrary to previous approaches, that rely on object-level models, we construct category-level models from CAD collections which are now widely available. To alleviate the need for huge amounts of labeled data, we develop a rendering pipeline that enables synthesis of large datasets from a limited amount of manually labeled data. Using data thus synthesized, we learn category-level models for object deformations in 3D, as well as discriminative object features in 2D. These category models are instance-independent and aid in the design of object landmark observations that can be incorporated into a generic monocular SLAM framework. Where typical object-SLAM approaches usually solve only for object and camera poses, we also estimate object shape on-the-fly, allowing for a wide range of objects from the category to be present in the scene. Moreover, since our 2D object features are learned discriminatively, the proposed object-SLAM system succeeds in several scenarios where sparse feature-based monocular SLAM fails due to insufficient features or parallax. Also, the proposed category-models help in object instance retrieval, useful for Augmented Reality (AR) applications. We evaluate the proposed framework on multiple challenging real-world scenes and show --- to the best of our knowledge --- first results of an instance-independent monocular object-SLAM system and the benefits it enjoys over feature-based SLAM methods.

Mithun Babu, Yash Oza, Arun Kumar Singh et al.

In this paper, we present a Model Predictive Control (MPC) framework based on path velocity decomposition paradigm for autonomous driving. The optimization underlying the MPC has a two layer structure wherein first, an appropriate path is computed for the vehicle followed by the computation of optimal forward velocity along it. The very nature of the proposed path velocity decomposition allows for seamless compatibility between the two layers of the optimization. A key feature of the proposed work is that it offloads most of the responsibility of collision avoidance to velocity optimization layer for which computationally efficient formulations can be derived. In particular, we extend our previously developed concept of time scaled collision cone (TSCC) constraints and formulate the forward velocity optimization layer as a convex quadratic programming problem. We perform validation on autonomous driving scenarios wherein proposed MPC repeatedly solves both the optimization layers in receding horizon manner to compute lane change, overtaking and merging maneuvers among multiple dynamic obstacles.

Roopal Nahar, Akanksha Baranwal, K. Madhava Krishna

Efficient and real time segmentation of color images has a variety of importance in many fields of computer vision such as image compression, medical imaging, mapping and autonomous navigation. Being one of the most computationally expensive operation, it is usually done through software imple- mentation using high-performance processors. In robotic systems, however, with the constrained platform dimensions and the need for portability, low power consumption and simultaneously the need for real time image segmentation, we envision hardware parallelism as the way forward to achieve higher acceleration. Field-programmable gate arrays (FPGAs) are among the best suited for this task as they provide high computing power in a small physical area. They exceed the computing speed of software based implementations by breaking the paradigm of sequential execution and accomplishing more per clock cycle operations by enabling hardware level parallelization at an architectural level. In this paper, we propose three novel architectures of a well known Efficient Graph based Image Segmentation algorithm. These proposed implementations optimizes time and power consumption when compared to software implementations. The hybrid design proposed, has notable furtherance of acceleration capabilities delivering atleast 2X speed gain over other implemen- tations, which henceforth allows real time image segmentation that can be deployed on Mobile Robotic systems.

Enna Sachdeva, Akash Singh, Vinay Rodrigues et al.

This paper presents a novel design of an Omnidirectional bendable Omnicrawler module- CObRaSO. Along with the longitudinal crawling and sideways rolling motion, the performance of the OmniCrawler is further enhanced by the introduction of Omnidirectional bending within the module, which is the key contribution of this paper. The Omnidirectional bending is achieved by an arrangement of two independent 1-DOF joints aligned at 90? w.r.t each other. The unique characteristic of this module is its ability to crawl in Omnidirectionally bent configuration which is achieved by a novel design of a 2-DOF roller chain and a backbone of a hybrid structure of a soft-rigid material. This hybrid structure provides compliant pathways for the lug-chain assembly to passively conform with the orientation of the module and crawl in Omnidirectional bent configuration, which makes this module one of its kind. Furthermore, we show that the unique modular design of CObRaSO unveils its versatility by achieving active compliance on an uneven surface, demonstrating its applications in different robotic platforms (an in-pipeline robot, Quadruped and snake robot) and exhibiting hybrid locomotion modes in various configurations of the robots. The mechanism and mobility characteristics of the proposed module have been verified with the aid of simulations and experiments on real robot prototype.

Akash Singh, Enna Sachdeva, Abhishek Sarkar et al.

This paper discusses the design of a novel compliant in-pipe climbing modular robot for small diameter pipes. The robot consists of a kinematic chain of 3 OmniCrawler modules with a link connected in between 2 adjacent modules via compliant joints. While the tank-like crawler mechanism provides good traction on low friction surfaces, its circular cross-section makes it holonomic. The holonomic motion assists it to re-align in a direction to avoid obstacles during motion as well as overcome turns with a minimal energy posture. Additionally, the modularity enables it to negotiate T-junction without motion singularity. The compliance is realized using 4 torsion springs incorporated in joints joining 3 modules with 2 links. For a desirable pipe diameter (\textØ 75mm), the springs' stiffness values are obtained by formulating a constraint optimization problem which has been simulated in ADAMS MSC and further validated on a real robot prototype. In order to negotiate smooth vertical bends and friction coefficient variations in pipes, the design was later modified by replacing springs with series elastic actuators (SEA) at 2 of the 4 joints.

Aseem Saxena, Harit Pandya, Gourav Kumar et al.

Present image based visual servoing approaches rely on extracting hand crafted visual features from an image. Choosing the right set of features is important as it directly affects the performance of any approach. Motivated by recent breakthroughs in performance of data driven methods on recognition and localization tasks, we aim to learn visual feature representations suitable for servoing tasks in unstructured and unknown environments. In this paper, we present an end-to-end learning based approach for visual servoing in diverse scenes where the knowledge of camera parameters and scene geometry is not available a priori. This is achieved by training a convolutional neural network over color images with synchronised camera poses. Through experiments performed in simulation and on a quadrotor, we demonstrate the efficacy and robustness of our approach for a wide range of camera poses in both indoor as well as outdoor environments.

Akash Singh, Enna Sachdeva, Abhishek Sarkar et al.

This paper presents a modular in-pipeline climbing robot with a novel compliant foldable OmniCrawler mechanism. The circular cross-section of the OmniCrawler module enables a holonomic motion to facilitate the alignment of the robot in the direction of bends. Additionally, the crawler mechanism provides a fair amount of traction, even on slippery surfaces. These advantages of crawler modules have been further supplemented by incorporating active compliance in the module itself which helps to negotiate sharp bends in small diameter pipes. The robot has a series of 3 such compliant foldable modules interconnected by the links via passive joints. For the desirable pipe diameter and curvature of the bends, the spring stiffness value for each passive joint is determined by formulating a constrained optimization problem using the quasi-static model of the robot. Moreover, a minimum friction coefficient value between the module-pipe surface which can be vertically climbed by the robot without slipping is estimated. The numerical simulation results have further been validated by experiments on real robot prototype.

Nazrul Haque, N Dinesh Reddy, K. Madhava Krishna

Dynamic scene understanding is a challenging problem and motion segmentation plays a crucial role in solving it. Incorporating semantics and motion enhances the overall perception of the dynamic scene. For applications of outdoor robotic navigation, joint learning methods have not been extensively used for extracting spatio-temporal features or adding different priors into the formulation. The task becomes even more challenging without stereo information being incorporated. This paper proposes an approach to fuse semantic features and motion clues using CNNs, to address the problem of monocular semantic motion segmentation. We deduce semantic and motion labels by integrating optical flow as a constraint with semantic features into dilated convolution network. The pipeline consists of three main stages i.e Feature extraction, Feature amplification and Multi Scale Context Aggregation to fuse the semantics and flow features. Our joint formulation shows significant improvements in monocular motion segmentation over the state of the art methods on challenging KITTI tracking dataset.

J. Krishna Murthy, G. V. Sai Krishna, Falak Chhaya et al.

We present an approach for reconstructing vehicles from a single (RGB) image, in the context of autonomous driving. Though the problem appears to be ill-posed, we demonstrate that prior knowledge about how 3D shapes of vehicles project to an image can be used to reason about the reverse process, i.e., how shapes (back-)project from 2D to 3D. We encode this knowledge in \emph{shape priors}, which are learnt over a small keypoint-annotated dataset. We then formulate a shape-aware adjustment problem that uses the learnt shape priors to recover the 3D pose and shape of a query object from an image. For shape representation and inference, we leverage recent successes of Convolutional Neural Networks (CNNs) for the task of object and keypoint localization, and train a novel cascaded fully-convolutional architecture to localize vehicle \emph{keypoints} in images. The shape-aware adjustment then robustly recovers shape (3D locations of the detected keypoints) while simultaneously filling in occluded keypoints. To tackle estimation errors incurred due to erroneously detected keypoints, we use an Iteratively Re-weighted Least Squares (IRLS) scheme for robust optimization, and as a by-product characterize noise models for each predicted keypoint. We evaluate our approach on autonomous driving benchmarks, and present superior results to existing monocular, as well as stereo approaches.