Inkyu Sa

Inkyu Sa, JongYoon Lim, Ho Seok Ahn et al.

This paper presents datasets utilised for synthetic near-infrared (NIR) image generation and bounding-box level fruit detection systems. It is undeniable that high-calibre machine learning frameworks such as Tensorflow or Pytorch, and large-scale ImageNet or COCO datasets with the aid of accelerated GPU hardware have pushed the limit of machine learning techniques for more than decades. Among these breakthroughs, a high-quality dataset is one of the essential building blocks that can lead to success in model generalisation and the deployment of data-driven deep neural networks. In particular, synthetic data generation tasks often require more training samples than other supervised approaches. Therefore, in this paper, we share the NIR+RGB datasets that are re-processed from two public datasets (i.e., nirscene and SEN12MS) and our novel NIR+RGB sweet pepper(capsicum) dataset. We quantitatively and qualitatively demonstrate that these NIR+RGB datasets are sufficient to be used for synthetic NIR image generation. We achieved Frechet Inception Distance (FID) of 11.36, 26.53, and 40.15 for nirscene1, SEN12MS, and sweet pepper datasets respectively. In addition, we release manual annotations of 11 fruit bounding boxes that can be exported as various formats using cloud service. Four newly added fruits [blueberry, cherry, kiwi, and wheat] compound 11 novel bounding box datasets on top of our previous work presented in the deepFruits project [apple, avocado, capsicum, mango, orange, rockmelon, strawberry]. The total number of bounding box instances of the dataset is 162k and it is ready to use from cloud service. For the evaluation of the dataset, Yolov5 single stage detector is exploited and reported impressive mean-average-precision,mAP[0.5:0.95] results of[min:0.49, max:0.812]. We hope these datasets are useful and serve as a baseline for the future studies.

Yongzhi Xu, Yonhon Ng, Yifu Wang et al.

3D Content Generation is at the heart of many computer graphics applications, including video gaming, film-making, virtual and augmented reality, etc. This paper proposes a novel deep-learning based approach for automatically generating interactive and playable 3D game scenes, all from the user's casual prompts such as a hand-drawn sketch. Sketch-based input offers a natural, and convenient way to convey the user's design intention in the content creation process. To circumvent the data-deficient challenge in learning (i.e. the lack of large training data of 3D scenes), our method leverages a pre-trained 2D denoising diffusion model to generate a 2D image of the scene as the conceptual guidance. In this process, we adopt the isometric projection mode to factor out unknown camera poses while obtaining the scene layout. From the generated isometric image, we use a pre-trained image understanding method to segment the image into meaningful parts, such as off-ground objects, trees, and buildings, and extract the 2D scene layout. These segments and layouts are subsequently fed into a procedural content generation (PCG) engine, such as a 3D video game engine like Unity or Unreal, to create the 3D scene. The resulting 3D scene can be seamlessly integrated into a game development environment and is readily playable. Extensive tests demonstrate that our method can efficiently generate high-quality and interactive 3D game scenes with layouts that closely follow the user's intention.

JongYoon Lim, Inkyu Sa, Bruce MacDonald et al.

This research explores using lightweight deep neural network architectures to enable the humanoid robot Pepper to understand American Sign Language (ASL) and facilitate non-verbal human-robot interaction. First, we introduce a lightweight and efficient model for ASL understanding optimized for embedded systems, ensuring rapid sign recognition while conserving computational resources. Building upon this, we employ large language models (LLMs) for intelligent robot interactions. Through intricate prompt engineering, we tailor interactions to allow the Pepper Robot to generate natural Co-Speech Gesture responses, laying the foundation for more organic and intuitive humanoid-robot dialogues. Finally, we present an integrated software pipeline, embodying advancements in a socially aware AI interaction model. Leveraging the Pepper Robot's capabilities, we demonstrate the practicality and effectiveness of our approach in real-world scenarios. The results highlight a profound potential for enhancing human-robot interaction through non-verbal interactions, bridging communication gaps, and making technology more accessible and understandable.

Andy Kweon, Vishnu Hu, Jong Yoon Lim et al.

As technology progresses, smart automated systems will serve an increasingly important role in the agricultural industry. Current existing vision systems for yield estimation face difficulties in occlusion and scalability as they utilize a camera system that is large and expensive, which are unsuitable for orchard environments. To overcome these problems, this paper presents a size measurement method combining a machine learning model and depth images captured from three low cost RGBD cameras to detect and measure the height and width of tomatoes. The performance of the presented system is evaluated on a lab environment with real tomato fruits and fake leaves to simulate occlusion in the real farm environment. To improve accuracy by addressing fruit occlusion, our three-camera system was able to achieve a height measurement accuracy of 0.9114 and a width accuracy of 0.9443.

Inkyu Sa, Mina Kamel, Michael Burri et al.

This paper describes an approach to building a cost-effective and research grade visual-inertial odometry aided vertical taking-off and landing (VTOL) platform. We utilize an off-the-shelf visual-inertial sensor, an onboard computer, and a quadrotor platform that are factory-calibrated and mass-produced, thereby sharing similar hardware and sensor specifications (e.g., mass, dimensions, intrinsic and extrinsic of camera-IMU systems, and signal-to-noise ratio). We then perform a system calibration and identification enabling the use of our visual-inertial odometry, multi-sensor fusion, and model predictive control frameworks with the off-the-shelf products. This implies that we can partially avoid tedious parameter tuning procedures for building a full system. The complete system is extensively evaluated both indoors using a motion capture system and outdoors using a laser tracker while performing hover and step responses, and trajectory following tasks in the presence of external wind disturbances. We achieve root-mean-square (RMS) pose errors between a reference and actual trajectories of 0.036m, while performing hover. We also conduct relatively long distance flight (~180m) experiments on a farm site and achieve 0.82% drift error of the total distance flight. This paper conveys the insights we acquired about the platform and sensor module and returns to the community as open-source code with tutorial documentation.

Inkyu Sa, Mina Kamel, Raghav Khanna et al.

This paper describes dynamic system identification, and full control of a cost-effective vertical take-off and landing (VTOL) multi-rotor micro-aerial vehicle (MAV) --- DJI Matrice 100. The dynamics of the vehicle and autopilot controllers are identified using only a built-in IMU and utilized to design a subsequent model predictive controller (MPC). Experimental results for the control performance are evaluated using a motion capture system while performing hover, step responses, and trajectory following tasks in the present of external wind disturbances. We achieve root-mean-square (RMS) errors between the reference and actual trajectory of x=0.021m, y=0.016m, z=0.029m, roll=0.392deg, pitch=0.618deg, and yaw=1.087deg while performing hover. This paper also conveys the insights we have gained about the platform and returned to the community through open-source code, and documentation.

JongYoon Lim, Inkyu Sa, Ho Seok Ahn et al.

Sentiment prediction remains a challenging and unresolved task in various research fields, including psychology, neuroscience, and computer science. This stems from its high degree of subjectivity and limited input sources that can effectively capture the actual sentiment. This can be even more challenging with only text-based input. Meanwhile, the rise of deep learning and an unprecedented large volume of data have paved the way for artificial intelligence to perform impressively accurate predictions or even human-level reasoning. Drawing inspiration from this, we propose a coverage-based sentiment and subsentence extraction system that estimates a span of input text and recursively feeds this information back to the networks. The predicted subsentence consists of auxiliary information expressing a sentiment. This is an important building block for enabling vivid and epic sentiment delivery (within the scope of this paper) and for other natural language processing tasks such as text summarisation and Q&A. Our approach outperforms the state-of-the-art approaches by a large margin in subsentence prediction (i.e., Average Jaccard scores from 0.72 to 0.89). For the evaluation, we designed rigorous experiments consisting of 24 ablation studies. Finally, our learned lessons are returned to the community by sharing software packages and a public dataset that can reproduce the results presented in this paper.

Nicolas Hudson, Fletcher Talbot, Mark Cox et al.

Heterogeneous teams of robots, leveraging a balance between autonomy and human interaction, bring powerful capabilities to the problem of exploring dangerous, unstructured subterranean environments. Here we describe the solution developed by Team CSIRO Data61, consisting of CSIRO, Emesent and Georgia Tech, during the DARPA Subterranean Challenge. These presented systems were fielded in the Tunnel Circuit in August 2019, the Urban Circuit in February 2020, and in our own Cave event, conducted in September 2020. A unique capability of the fielded team is the homogeneous sensing of the platforms utilised, which is leveraged to obtain a decentralised multi-agent SLAM solution on each platform (both ground agents and UAVs) using peer-to-peer communications. This enabled a shift in focus from constructing a pervasive communications network to relying on multi-agent autonomy, motivated by experiences in early circuit events. These experiences also showed the surprising capability of rugged tracked platforms for challenging terrain, which in turn led to the heterogeneous team structure based on a BIA5 OzBot Titan ground robot and an Emesent Hovermap UAV, supplemented by smaller tracked or legged ground robots. The ground agents use a common CatPack perception module, which allowed reuse of the perception and autonomy stack across all ground agents with minimal adaptation.

Thomas Hines, Kazys Stepanas, Fletcher Talbot et al.

This paper presents an autonomous navigation system for ground robots traversing aggressive unstructured terrain through a cohesive arrangement of mapping, deliberative planning and reactive behaviour modules. All systems are aware of terrain slope, visibility and vehicle orientation, enabling robots to recognize, plan and react around unobserved areas and overcome negative obstacles, slopes, steps, overhangs and narrow passageways. This is one of pioneer works to explicitly and simultaneously couple mapping, planning and reactive components in dealing with negative obstacles. The system was deployed on three heterogeneous ground robots for the DARPA Subterranean Challenge, and we present results in Urban and Cave environments, along with simulated scenarios, that demonstrate this approach.

Sirish Srinivasan, Inkyu Sa, Alex Zyner et al.

Velocity estimation plays a central role in driverless vehicles, but standard and affordable methods struggle to cope with extreme scenarios like aggressive maneuvers due to the presence of high sideslip. To solve this, autonomous race cars are usually equipped with expensive external velocity sensors. In this paper, we present an end-to-end recurrent neural network that takes available raw sensors as input (IMU, wheel odometry, and motor currents) and outputs velocity estimates. The results are compared to two state-of-the-art Kalman filters, which respectively include and exclude expensive velocity sensors. All methods have been extensively tested on a formula student driverless race car with very high sideslip (10° at the rear axle) and slip ratio (~20%), operating close to the limits of handling. The proposed network is able to estimate lateral velocity up to 15x better than the Kalman filter with the equivalent sensor input and matches (0.06 m/s RMSE) the Kalman filter with the expensive velocity sensor setup.

Alberto Pretto, Stéphanie Aravecchia, Wolfram Burgard et al.

The application of autonomous robots in agriculture is gaining increasing popularity thanks to the high impact it may have on food security, sustainability, resource use efficiency, reduction of chemical treatments, and the optimization of human effort and yield. With this vision, the Flourish research project aimed to develop an adaptable robotic solution for precision farming that combines the aerial survey capabilities of small autonomous unmanned aerial vehicles (UAVs) with targeted intervention performed by multi-purpose unmanned ground vehicles (UGVs). This paper presents an overview of the scientific and technological advances and outcomes obtained in the project. We introduce multi-spectral perception algorithms and aerial and ground-based systems developed for monitoring crop density, weed pressure, crop nitrogen nutrition status, and to accurately classify and locate weeds. We then introduce the navigation and mapping systems tailored to our robots in the agricultural environment, as well as the modules for collaborative mapping. We finally present the ground intervention hardware, software solutions, and interfaces we implemented and tested in different field conditions and with different crops. We describe a real use case in which a UAV collaborates with a UGV to monitor the field and to perform selective spraying without human intervention.

Juraj Kabzan, Miguel de la Iglesia Valls, Victor Reijgwart et al.

This paper presents the algorithms and system architecture of an autonomous racecar. The introduced vehicle is powered by a software stack designed for robustness, reliability, and extensibility. In order to autonomously race around a previously unknown track, the proposed solution combines state of the art techniques from different fields of robotics. Specifically, perception, estimation, and control are incorporated into one high-performance autonomous racecar. This complex robotic system, developed by AMZ Driverless and ETH Zurich, finished 1st overall at each competition we attended: Formula Student Germany 2017, Formula Student Italy 2018 and Formula Student Germany 2018. We discuss the findings and learnings from these competitions and present an experimental evaluation of each module of our solution.

Chris Lehnert, Chris McCool, Inkyu Sa et al.

Using robots to harvest sweet peppers in protected cropping environments has remained unsolved despite considerable effort by the research community over several decades. In this paper, we present the robotic harvester, Harvey, designed for sweet peppers in protected cropping environments that achieved a 76.5% success rate (within a modified scenario) which improves upon our prior work which achieved 58% and related sweet pepper harvesting work which achieved 33\%. This improvement was primarily achieved through the introduction of a novel peduncle segmentation system using an efficient deep convolutional neural network, in conjunction with 3D post-filtering to detect the critical cutting location. We benchmark the peduncle segmentation against prior art demonstrating a considerable improvement in performance with an F_1 score of 0.564 compared to 0.302. The robotic harvester uses a perception pipeline to detect a target sweet pepper and an appropriate grasp and cutting pose used to determine the trajectory of a multi-modal harvesting tool to grasp the sweet pepper and cut it from the plant. A novel decoupling mechanism enables the gripping and cutting operations to be performed independently. We perform an in-depth analysis of the full robotic harvesting system to highlight bottlenecks and failure points that future work could address.

Nikhil Bharadwaj Gosala, Andreas Bühler, Manish Prajapat et al.

In autonomous racing, vehicles operate close to the limits of handling and a sensor failure can have critical consequences. To limit the impact of such failures, this paper presents the redundant perception and state estimation approaches developed for an autonomous race car. Redundancy in perception is achieved by estimating the color and position of the track delimiting objects using two sensor modalities independently. Specifically, learning-based approaches are used to generate color and pose estimates, from LiDAR and camera data respectively. The redundant perception inputs are fused by a particle filter based SLAM algorithm that operates in real-time. Velocity is estimated using slip dynamics, with reliability being ensured through a probabilistic failure detection algorithm. The sub-modules are extensively evaluated in real-world racing conditions using the autonomous race car "gotthard driverless", achieving lateral accelerations up to 1.7G and a top speed of 90km/h.

Marija Popovic, Teresa Vidal-Calleja, Gregory Hitz et al.

Unmanned Aerial Vehicles (UAVs) represent a new frontier in a wide range of monitoring and research applications. To fully leverage their potential, a key challenge is planning missions for efficient data acquisition in complex environments. To address this issue, this article introduces a general Informative Path Planning (IPP) framework for monitoring scenarios using an aerial robot, focusing on problems in which the value of sensor information is unevenly distributed in a target area and unknown a priori . The approach is capable of learning and focusing on regions of interest via adaptation to map either discrete or continuous variables on the terrain using variable-resolution data received from probabilistic sensors. During a mission, the terrain maps built online are used to plan information-rich trajectories in continuous 3-D space by optimizing initial solutions obtained by a coarse grid search. Extensive simulations show that our approach is more efficient than existing methods. We also demonstrate its real-time application on a photorealistic mapping scenario using a publicly available dataset and demonstrate a proof of concept for an agricultural monitoring task.

Inkyu Sa, Marija Popovic, Raghav Khanna et al.

We present a novel weed segmentation and mapping framework that processes multispectral images obtained from an unmanned aerial vehicle (UAV) using a deep neural network (DNN). Most studies on crop/weed semantic segmentation only consider single images for processing and classification. Images taken by UAVs often cover only a few hundred square meters with either color only or color and near-infrared (NIR) channels. Computing a single large and accurate vegetation map (e.g., crop/weed) using a DNN is non-trivial due to difficulties arising from: (1) limited ground sample distances (GSDs) in high-altitude datasets, (2) sacrificed resolution resulting from downsampling high-fidelity images, and (3) multispectral image alignment. To address these issues, we adopt a stand sliding window approach that operates on only small portions of multispectral orthomosaic maps (tiles), which are channel-wise aligned and calibrated radiometrically across the entire map. We define the tile size to be the same as that of the DNN input to avoid resolution loss. Compared to our baseline model (i.e., SegNet with 3 channel RGB inputs) yielding an area under the curve (AUC) of [background=0.607, crop=0.681, weed=0.576], our proposed model with 9 input channels achieves [0.839, 0.863, 0.782]. Additionally, we provide an extensive analysis of 20 trained models, both qualitatively and quantitatively, in order to evaluate the effects of varying input channels and tunable network hyperparameters. Furthermore, we release a large sugar beet/weed aerial dataset with expertly guided annotations for further research in the fields of remote sensing, precision agriculture, and agricultural robotics.

Ho Seok Ahn, Feras Dayoub, Marija Popovic et al.

Horticultural enterprises are becoming more sophisticated as the range of the crops they target expands. Requirements for enhanced efficiency and productivity have driven the demand for automating on-field operations. However, various problems remain yet to be solved for their reliable, safe deployment in real-world scenarios. This paper examines major research trends and current challenges in horticultural robotics. Specifically, our work focuses on sensing and perception in the three main horticultural procedures: pollination, yield estimation, and harvesting. For each task, we expose major issues arising from the unstructured, cluttered, and rugged nature of field environments, including variable lighting conditions and difficulties in fruit-specific detection, and highlight promising contemporary studies.

Miguel de la Iglesia Valls, Hubertus Franciscus Cornelis Hendrikx, Victor Reijgwart et al.

This paper introduces flüela driverless: the first autonomous racecar to win a Formula Student Driverless competition. In this competition, among other challenges, an autonomous racecar is tasked to complete 10 laps of a previously unknown racetrack as fast as possible and using only onboard sensing and computing. The key components of flüela's design are its modular redundant sub-systems that allow robust performance despite challenging perceptual conditions or partial system failures. The paper presents the integration of key components of our autonomous racecar, i.e., system design, EKF-based state estimation, LiDAR-based perception, and particle filter-based SLAM. We perform an extensive experimental evaluation on real-world data, demonstrating the system's effectiveness by outperforming the next-best ranking team by almost half the time required to finish a lap. The autonomous racecar reaches lateral and longitudinal accelerations comparable to those achieved by experienced human drivers.

Inkyu Sa, Zetao Chen, Marija Popovic et al.

Selective weed treatment is a critical step in autonomous crop management as related to crop health and yield. However, a key challenge is reliable, and accurate weed detection to minimize damage to surrounding plants. In this paper, we present an approach for dense semantic weed classification with multispectral images collected by a micro aerial vehicle (MAV). We use the recently developed encoder-decoder cascaded Convolutional Neural Network (CNN), Segnet, that infers dense semantic classes while allowing any number of input image channels and class balancing with our sugar beet and weed datasets. To obtain training datasets, we established an experimental field with varying herbicide levels resulting in field plots containing only either crop or weed, enabling us to use the Normalized Difference Vegetation Index (NDVI) as a distinguishable feature for automatic ground truth generation. We train 6 models with different numbers of input channels and condition (fine-tune) it to achieve about 0.8 F1-score and 0.78 Area Under the Curve (AUC) classification metrics. For model deployment, an embedded GPU system (Jetson TX2) is tested for MAV integration. Dataset used in this paper is released to support the community and future work.

Jemin Hwangbo, Inkyu Sa, Roland Siegwart et al.

In this paper, we present a method to control a quadrotor with a neural network trained using reinforcement learning techniques. With reinforcement learning, a common network can be trained to directly map state to actuator command making any predefined control structure obsolete for training. Moreover, we present a new learning algorithm which differs from the existing ones in certain aspects. Our algorithm is conservative but stable for complicated tasks. We found that it is more applicable to controlling a quadrotor than existing algorithms. We demonstrate the performance of the trained policy both in simulation and with a real quadrotor. Experiments show that our policy network can react to step response relatively accurately. With the same policy, we also demonstrate that we can stabilize the quadrotor in the air even under very harsh initialization (manually throwing it upside-down in the air with an initial velocity of 5 m/s). Computation time of evaluating the policy is only 7 μs per time step which is two orders of magnitude less than common trajectory optimization algorithms with an approximated model.

Marija Popovic, Teresa Vidal-Calleja, Gregory Hitz et al.

Unmanned aerial vehicles (UAVs) can offer timely and cost-effective delivery of high-quality sensing data. How- ever, deciding when and where to take measurements in complex environments remains an open challenge. To address this issue, we introduce a new multiresolution mapping approach for informative path planning in terrain monitoring using UAVs. Our strategy exploits the spatial correlation encoded in a Gaussian Process model as a prior for Bayesian data fusion with probabilistic sensors. This allows us to incorporate altitude-dependent sensor models for aerial imaging and perform constant-time measurement updates. The resulting maps are used to plan information-rich trajectories in continuous 3-D space through a combination of grid search and evolutionary optimization. We evaluate our framework on the application of agricultural biomass monitoring. Extensive simulations show that our planner performs better than existing methods, with mean error reductions of up to 45% compared to traditional "lawnmower" coverage. We demonstrate proof of concept using a multirotor to map color in different environments.

Inkyu Sa, Chris Lehnert, Andrew English et al.

This paper presents a 3D visual detection method for the challenging task of detecting peduncles of sweet peppers (Capsicum annuum) in the field. Cutting the peduncle cleanly is one of the most difficult stages of the harvesting process, where the peduncle is the part of the crop that attaches it to the main stem of the plant. Accurate peduncle detection in 3D space is therefore a vital step in reliable autonomous harvesting of sweet peppers, as this can lead to precise cutting while avoiding damage to the surrounding plant. This paper makes use of both colour and geometry information acquired from an RGB-D sensor and utilises a supervised-learning approach for the peduncle detection task. The performance of the proposed method is demonstrated and evaluated using qualitative and quantitative results (the Area-Under-the-Curve (AUC) of the detection precision-recall curve). We are able to achieve an AUC of 0.71 for peduncle detection on field-grown sweet peppers. We release a set of manually annotated 3D sweet pepper and peduncle images to assist the research community in performing further research on this topic.

Marija Popovic, Gregory Hitz, Juan Nieto et al.

In this paper, we introduce an informative path planning (IPP) framework for active classification using unmanned aerial vehicles (UAVs). Our algorithm uses a combination of global viewpoint selection and evolutionary optimization to refine the planned trajectory in continuous 3D space while satisfying dynamic constraints. Our approach is evaluated on the application of weed detection for precision agriculture. We model the presence of weeds on farmland using an occupancy grid and generate adaptive plans according to information-theoretic objectives, enabling the UAV to gather data efficiently. We validate our approach in simulation by comparing against existing methods, and study the effects of different planning strategies. Our results show that the proposed algorithm builds maps with over 50% lower entropy compared to traditional "lawnmower" coverage in the same amount of time. We demonstrate the planning scheme on a multirotor platform with different artificial farmland set-ups.