Ali-akbar Agha-mohammadi

Robin Schmid, Deegan Atha, Frederik Schöller et al. · eth-zurich

Navigating off-road with a fast autonomous vehicle depends on a robust perception system that differentiates traversable from non-traversable terrain. Typically, this depends on a semantic understanding which is based on supervised learning from images annotated by a human expert. This requires a significant investment in human time, assumes correct expert classification, and small details can lead to misclassification. To address these challenges, we propose a method for predicting high- and low-risk terrains from only past vehicle experience in a self-supervised fashion. First, we develop a tool that projects the vehicle trajectory into the front camera image. Second, occlusions in the 3D representation of the terrain are filtered out. Third, an autoencoder trained on masked vehicle trajectory regions identifies low- and high-risk terrains based on the reconstruction error. We evaluated our approach with two models and different bottleneck sizes with two different training and testing sites with a fourwheeled off-road vehicle. Comparison with two independent test sets of semantic labels from similar terrain as training sites demonstrates the ability to separate the ground as low-risk and the vegetation as high-risk with 81.1% and 85.1% accuracy.

Joshua Ott, Sung-Kyun Kim, Amanda Bouman et al.

Robotic exploration of unknown environments is fundamentally a problem of decision making under uncertainty where the robot must account for uncertainty in sensor measurements, localization, action execution, as well as many other factors. For large-scale exploration applications, autonomous systems must overcome the challenges of sequentially deciding which areas of the environment are valuable to explore while safely evaluating the risks associated with obstacles and hazardous terrain. In this work, we propose a risk-aware meta-level decision making framework to balance the tradeoffs associated with local and global exploration. Meta-level decision making builds upon classical hierarchical coverage planners by switching between local and global policies with the overall objective of selecting the policy that is most likely to maximize reward in a stochastic environment. We use information about the environment history, traversability risk, and kinodynamic constraints to reason about the probability of successful policy execution to switch between local and global policies. We have validated our solution in both simulation and on a variety of large-scale real world hardware tests. Our results show that by balancing local and global exploration we are able to significantly explore large-scale environments more efficiently.

Nikolaos Stathoulopoulos, Anton Koval, Ali-akbar Agha-mohammadi et al.

This article presents a 3D point cloud map-merging framework for egocentric heterogeneous multi-robot exploration, based on overlap detection and alignment, that is independent of a manual initial guess or prior knowledge of the robots' poses. The novel proposed solution utilizes state-of-the-art place recognition learned descriptors, that through the framework's main pipeline, offer a fast and robust region overlap estimation, hence eliminating the need for the time-consuming global feature extraction and feature matching process that is typically used in 3D map integration. The region overlap estimation provides a homogeneous rigid transform that is applied as an initial condition in the point cloud registration algorithm Fast-GICP, which provides the final and refined alignment. The efficacy of the proposed framework is experimentally evaluated based on multiple field multi-robot exploration missions in underground environments, where both ground and aerial robots are deployed, with different sensor configurations.

Jason M. Gregory, Sarah Al-Hussaini, Ali-akbar Agha-mohammadi et al.

Experimental design in field robotics is an adaptive human-in-the-loop decision-making process in which an experimenter learns about system performance and limitations through interactions with a robot in the form of constructed experiments. This can be challenging because of system complexity, the need to operate in unstructured environments, and the competing objectives of maximizing information gain while simultaneously minimizing experimental costs. Based on the successes in other domains, we propose the use of a Decision Support System (DSS) to amplify the human's decision-making abilities, overcome their inherent shortcomings, and enable principled decision-making in field experiments. In this work, we propose common terminology and a six-stage taxonomy of DSSs specifically for adaptive experimental design of more informative tests and reduced experimental costs. We construct and present our taxonomy using examples and trends from DSS literature, including works involving artificial intelligence and Intelligent DSSs. Finally, we identify critical technical gaps and opportunities for future research to direct the scientific community in the pursuit of next-generation DSSs for experimental design.

Mario A. V. Saucedo, Akash Patel, Rucha Sawlekar et al.

In this article, we propose a novel LiDAR and event camera fusion modality for subterranean (SubT) environments for fast and precise object and human detection in a wide variety of adverse lighting conditions, such as low or no light, high-contrast zones and in the presence of blinding light sources. In the proposed approach, information from the event camera and LiDAR are fused to localize a human or an object-of-interest in a robot's local frame. The local detection is then transformed into the inertial frame and used to set references for a Nonlinear Model Predictive Controller (NMPC) for reactive tracking of humans or objects in SubT environments. The proposed novel fusion uses intensity filtering and K-means clustering on the LiDAR point cloud and frequency filtering and connectivity clustering on the events induced in an event camera by the returning LiDAR beams. The centroids of the clusters in the event camera and LiDAR streams are then paired to localize reflective markers present on safety vests and signs in SubT environments. The efficacy of the proposed scheme has been experimentally validated in a real SubT environment (a mine) with a Pioneer 3AT mobile robot. The experimental results show real-time performance for human detection and the NMPC-based controller allows for reactive tracking of a human or object of interest, even in complete darkness.

Marcel Kaufmann, Robert Trybula, Ryan Stonebraker et al.

Real-world deployment of new technology and capabilities can be daunting. The recent DARPA Subterranean (SubT) Challenge, for instance, aimed at the advancement of robotic platforms and autonomy capabilities in three one-year development pushes. While multi-agent systems are traditionally deployed in controlled and structured environments that allow for controlled testing (e.g., warehouses), the SubT challenge targeted various types of unknown underground environments that imposed the risk of robot loss in the case of failure. In this work, we introduce a video game-inspired interface, an autonomous mission assistant, and test and deploy these using a heterogeneous multi-agent system in challenging environments. This work leads to improved human-supervisory control for a multi-agent system reducing overhead from application switching, task planning, execution, and verification while increasing available exploration time with this human-autonomy teaming platform.

Haoyang He, Jay Patrikar, Dong-Ki Kim et al.

Recent advances in video world modeling have enabled large-scale generative models to simulate embodied environments with high visual fidelity, providing strong priors for prediction, planning, and control. Yet, despite their realism, these models often lack geometric grounding, limiting their use in navigation tasks that require spatial coherence and long-horizon stability. We introduce Reinforcement Learning with World Grounding (RLWG), a self-supervised post-training framework that aligns pretrained world models with a physically verifiable structure through geometric and perceptual rewards. Analogous to reinforcement learning from verifiable feedback (RLVR) in language models, RLWG can use multiple rewards that measure pose cycle-consistency, depth reprojection, and temporal coherence. We instantiate this framework with GrndCtrl, a reward-aligned adaptation method based on Group Relative Policy Optimization (GRPO), yielding world models that maintain stable trajectories, consistent geometry, and reliable rollouts for embodied navigation. Like post-training alignment in large language models, GrndCtrl leverages verifiable rewards to bridge generative pretraining and grounded behavior, achieving superior spatial coherence and navigation stability over supervised fine-tuning in outdoor environments.

Aileen Liao, Dong-Ki Kim, Max Olan Smith et al.

As a robot senses and selects actions, the world keeps changing. This inference delay creates a gap of tens to hundreds of milliseconds between the observed state and the state at execution. In this work, we take the natural generalization from zero delay to measured delay during training and inference. We introduce Delay-Aware Diffusion Policy (DA-DP), a framework for explicitly incorporating inference delays into policy learning. DA-DP corrects zero-delay trajectories to their delay-compensated counterparts, and augments the policy with delay conditioning. We empirically validate DA-DP on a variety of tasks, robots, and delays and find its success rate more robust to delay than delay-unaware methods. DA-DP is architecture agnostic and transfers beyond diffusion policies, offering a general pattern for delay-aware imitation learning. More broadly, DA-DP encourages evaluation protocols that report performance as a function of measured latency, not just task difficulty.

Yafei Hu, Quanting Xie, Vidhi Jain et al. · cmu

Building general-purpose robots that operate seamlessly in any environment, with any object, and utilizing various skills to complete diverse tasks has been a long-standing goal in Artificial Intelligence. However, as a community, we have been constraining most robotic systems by designing them for specific tasks, training them on specific datasets, and deploying them within specific environments. These systems require extensively-labeled data and task-specific models. When deployed in real-world scenarios, such systems face several generalization issues and struggle to remain robust to distribution shifts. Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i.e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of general-purpose robotics, and also exploring (ii) what a robotics-specific foundation model would look like. We begin by providing a generalized formulation of how foundation models are used in robotics, and the fundamental barriers to making generalist robots universally applicable. Next, we establish a taxonomy to discuss current work exploring ways to leverage existing foundation models for robotics and develop ones catered to robotics. Finally, we discuss key challenges and promising future directions in using foundation models for enabling general-purpose robotic systems. We encourage readers to view our living GitHub repository 2 of resources, including papers reviewed in this survey, as well as related projects and repositories for developing foundation models for robotics.

Nikolaos Stathoulopoulos, Björn Lindqvist, Anton Koval et al.

In this article, a novel approach for merging 3D point cloud maps in the context of egocentric multi-robot exploration is presented. Unlike traditional methods, the proposed approach leverages state-of-the-art place recognition and learned descriptors to efficiently detect overlap between maps, eliminating the need for the time-consuming global feature extraction and feature matching process. The estimated overlapping regions are used to calculate a homogeneous rigid transform, which serves as an initial condition for the GICP point cloud registration algorithm to refine the alignment between the maps. The advantages of this approach include faster processing time, improved accuracy, and increased robustness in challenging environments. Furthermore, the effectiveness of the proposed framework is successfully demonstrated through multiple field missions of robot exploration in a variety of different underground environments.

Jinrae Kim, Sunggoo Jung, Sung-Kyun Kim et al.

A staircase localization method is proposed for robots to explore urban environments autonomously. The proposed method employs a modular design in the form of a cascade pipeline consisting of three modules of stair detection, line segment detection, and stair localization modules. The stair detection module utilizes an object detection algorithm based on deep learning to generate a region of interest (ROI). From the ROI, line segment features are extracted using a deep line segment detection algorithm. The extracted line segments are used to localize a staircase in terms of position, orientation, and stair direction. The stair detection and localization are performed only with a single RGB-D camera. Each component of the proposed pipeline does not need to be designed particularly for staircases, which makes it easy to maintain the whole pipeline and replace each component with state-of-the-art deep learning detection techniques. The results of real-world experiments show that the proposed method can perform accurate stair detection and localization during autonomous exploration for various structured and unstructured upstairs and downstairs with shadows, dirt, and occlusions by artificial and natural objects.

Muhammad Fadhil Ginting, Dong-Ki Kim, Xiangyun Meng et al.

As robots become increasingly capable of operating over extended periods -- spanning days, weeks, and even months -- they are expected to accumulate knowledge of their environments and leverage this experience to assist humans more effectively. This paper studies the problem of Long-term Active Embodied Question Answering (LA-EQA), a new task in which a robot must both recall past experiences and actively explore its environment to answer complex, temporally-grounded questions. Unlike traditional EQA settings, which typically focus either on understanding the present environment alone or on recalling a single past observation, LA-EQA challenges an agent to reason over past, present, and possible future states, deciding when to explore, when to consult its memory, and when to stop gathering observations and provide a final answer. Standard EQA approaches based on large models struggle in this setting due to limited context windows, absence of persistent memory, and an inability to combine memory recall with active exploration. To address this, we propose a structured memory system for robots, inspired by the mind palace method from cognitive science. Our method encodes episodic experiences as scene-graph-based world instances, forming a reasoning and planning algorithm that enables targeted memory retrieval and guided navigation. To balance the exploration-recall trade-off, we introduce value-of-information-based stopping criteria that determines when the agent has gathered sufficient information. We evaluate our method on real-world experiments and introduce a new benchmark that spans popular simulation environments and actual industrial sites. Our approach significantly outperforms state-of-the-art baselines, yielding substantial gains in both answer accuracy and exploration efficiency.

Kenny Chen, Brett T. Lopez, Ali-akbar Agha-mohammadi et al.

Field robotics in perceptually-challenging environments require fast and accurate state estimation, but modern LiDAR sensors quickly overwhelm current odometry algorithms. To this end, this paper presents a lightweight frontend LiDAR odometry solution with consistent and accurate localization for computationally-limited robotic platforms. Our Direct LiDAR Odometry (DLO) method includes several key algorithmic innovations which prioritize computational efficiency and enables the use of dense, minimally-preprocessed point clouds to provide accurate pose estimates in real-time. This is achieved through a novel keyframing system which efficiently manages historical map information, in addition to a custom iterative closest point solver for fast point cloud registration with data structure recycling. Our method is more accurate with lower computational overhead than the current state-of-the-art and has been extensively evaluated in multiple perceptually-challenging environments on aerial and legged robots as part of NASA JPL Team CoSTAR's research and development efforts for the DARPA Subterranean Challenge.

Björn Lindqvist, Christoforos Kanellakis, Sina Sharif Mansouri et al.

This work establishes COMPRA, a compact and reactive autonomy framework for fast deployment of Micro Aerial Vehicles (MAVs) in subterranean Search-and-Rescue (SAR) missions. A COMPRA-enabled MAV is able to autonomously explore previously unknown areas while specific mission criteria are considered e.g. an object of interest is identified and localized, the remaining useful battery life, the overall desired exploration mission duration. The proposed architecture follows a low-complexity algorithmic design to facilitate fully on-board computations, including nonlinear control, state-estimation, navigation, exploration behavior and object localization capabilities. The framework is mainly structured around a reactive local avoidance planner, based on enhanced Potential Field concepts and using instantaneous 3D pointclouds, as well as a computationally efficient heading regulation technique, based on depth images from an instantaneous camera stream. Those techniques decouple the collision-free path generation from the dependency of a global map and are capable of handling imprecise localization occasions. Field experimental verification of the overall architecture is performed in relevant unknown Global Positioning System (GPS)-denied environments.

David D. Fan, Sharmita Dey, Ali-akbar Agha-mohammadi et al.

One of the main challenges in autonomous robotic exploration and navigation in unknown and unstructured environments is determining where the robot can or cannot safely move. A significant source of difficulty in this determination arises from stochasticity and uncertainty, coming from localization error, sensor sparsity and noise, difficult-to-model robot-ground interactions, and disturbances to the motion of the vehicle. Classical approaches to this problem rely on geometric analysis of the surrounding terrain, which can be prone to modeling errors and can be computationally expensive. Moreover, modeling the distribution of uncertain traversability costs is a difficult task, compounded by the various error sources mentioned above. In this work, we take a principled learning approach to this problem. We introduce a neural network architecture for robustly learning the distribution of traversability costs. Because we are motivated by preserving the life of the robot, we tackle this learning problem from the perspective of learning tail-risks, i.e. the Conditional Value-at-Risk (CVaR). We show that this approach reliably learns the expected tail risk given a desired probability risk threshold between 0 and 1, producing a traversability costmap which is more robust to outliers, more accurately captures tail risks, and is more computationally efficient, when compared against baselines. We validate our method on data collected a legged robot navigating challenging, unstructured environments including an abandoned subway, limestone caves, and lava tube caves.

Dongliang Zheng, Jack Ridderhof, Panagiotis Tsiotras et al.

A new belief space planning algorithm, called covariance steering Belief RoadMap (CS-BRM), is introduced, which is a multi-query algorithm for motion planning of dynamical systems under simultaneous motion and observation uncertainties. CS-BRM extends the probabilistic roadmap (PRM) approach to belief spaces and is based on the recently developed theory of covariance steering (CS) that enables guaranteed satisfaction of terminal belief constraints in finite-time. The nodes in the CS-BRM are sampled in belief space and represent distributions of the system states. A covariance steering controller steers the system from one BRM node to another, thus acting as an edge controller of the corresponding belief graph that ensures belief constraint satisfaction. After the edge controller is computed, a specific edge cost is assigned to that edge. The CS-BRM algorithm allows the sampling of non-stationary belief nodes, and thus is able to explore the velocity space and find efficient motion plans. The performance of CS-BRM is evaluated and compared to a previous belief space planning method, demonstrating the benefits of the proposed approach.

Björn Lindqvist, Ali-akbar Agha-mohammadi, George Nikolakopoulos

This article establishes the Exploration-RRT algorithm: A novel general-purpose combined exploration and pathplanning algorithm, based on a multi-goal Rapidly-Exploring Random Trees (RRT) framework. Exploration-RRT (ERRT) has been specifically designed for utilization in 3D exploration missions, with partially or completely unknown and unstructured environments. The novel proposed ERRT is based on a multi-objective optimization framework and it is able to take under consideration the potential information gain, the distance travelled, and the actuation costs, along trajectories to pseudo-random goals, generated from considering the on-board sensor model and the non-linear model of the utilized platform. In this article, the algorithmic pipeline of the ERRT will be established and the overall applicability and efficiency of the proposed scheme will be presented on an application with an Unmanned Aerial Vehicle (UAV) model, equipped with a 3D lidar, in a simulated operating environment, with the goal of exploring a completely unknown area as efficiently and quickly as possible

Seyed Fakoorian, Angel Santamaria-Navarro, Brett T. Lopez et al.

This work proposes a resilient and adaptive state estimation framework for robots operating in perceptually-degraded environments. The approach, called Adaptive Maximum Correntropy Criterion Kalman Filtering (AMCCKF), is inherently robust to corrupted measurements, such as those containing jumps or general non-Gaussian noise, and is able to modify filter parameters online to improve performance. Two separate methods are developed -- the Variational Bayesian AMCCKF (VB-AMCCKF) and Residual AMCCKF (R-AMCCKF) -- that modify the process and measurement noise models in addition to the bandwidth of the kernel function used in MCCKF based on the quality of measurements received. The two approaches differ in computational complexity and overall performance which is experimentally analyzed. The method is demonstrated in real experiments on both aerial and ground robots and is part of the solution used by the COSTAR team participating at the DARPA Subterranean Challenge.

Sunggoo Jung, Hanseob Lee, David Hyunchul Shim et al.

Collision-free path planning is an essential requirement for autonomous exploration in unknown environments, especially when operating in confined spaces or near obstacles. This study presents an autonomous exploration technique using a small drone. A local end-point selection method is designed using LiDAR range measurement and then generates the path from the current position to the selected end-point. The generated path shows the consistent collision-free path in real-time by adopting the Euclidean signed distance field-based grid-search method. The simulation results consistently showed the safety, and reliability of the proposed path-planning method. Real-world experiments are conducted in three different mines, demonstrating successful autonomous exploration flight in environments with various structural conditions. The results showed the high capability of the proposed flight autonomy framework for lightweight aerial-robot systems. Besides, our drone performs an autonomous mission during our entry at the Tunnel Circuit competition (Phase 1) of the DARPA Subterranean Challenge.

David D. Fan, Kyohei Otsu, Yuki Kubo et al.

Although ground robotic autonomy has gained widespread usage in structured and controlled environments, autonomy in unknown and off-road terrain remains a difficult problem. Extreme, off-road, and unstructured environments such as undeveloped wilderness, caves, and rubble pose unique and challenging problems for autonomous navigation. To tackle these problems we propose an approach for assessing traversability and planning a safe, feasible, and fast trajectory in real-time. Our approach, which we name STEP (Stochastic Traversability Evaluation and Planning), relies on: 1) rapid uncertainty-aware mapping and traversability evaluation, 2) tail risk assessment using the Conditional Value-at-Risk (CVaR), and 3) efficient risk and constraint-aware kinodynamic motion planning using sequential quadratic programming-based (SQP) model predictive control (MPC). We analyze our method in simulation and validate its efficacy on wheeled and legged robotic platforms exploring extreme terrains including an abandoned subway and an underground lava tube.

Sung-Kyun Kim, Amanda Bouman, Gautam Salhotra et al.

In order for an autonomous robot to efficiently explore an unknown environment, it must account for uncertainty in sensor measurements, hazard assessment, localization, and motion execution. Making decisions for maximal reward in a stochastic setting requires value learning and policy construction over a belief space, i.e., probability distribution over all possible robot-world states. However, belief space planning in a large spatial environment over long temporal horizons suffers from severe computational challenges. Moreover, constructed policies must safely adapt to unexpected changes in the belief at runtime. This work proposes a scalable value learning framework, PLGRIM (Probabilistic Local and Global Reasoning on Information roadMaps), that bridges the gap between (i) local, risk-aware resiliency and (ii) global, reward-seeking mission objectives. Leveraging hierarchical belief space planners with information-rich graph structures, PLGRIM addresses large-scale exploration problems while providing locally near-optimal coverage plans. We validate our proposed framework with high-fidelity dynamic simulations in diverse environments and on physical robots in Martian-analog lava tubes.

Kamak Ebadi, Matteo Palieri, Sally Wood et al.

Enabling fully autonomous robots capable of navigating and exploring large-scale, unknown and complex environments has been at the core of robotics research for several decades. A key requirement in autonomous exploration is building accurate and consistent maps of the unknown environment that can be used for reliable navigation. Loop closure detection, the ability to assert that a robot has returned to a previously visited location, is crucial for consistent mapping as it reduces the drift caused by error accumulation in the estimated robot trajectory. Moreover, in multi-robot systems, loop closures enable merging local maps obtained by a team of robots into a consistent global map of the environment. In this paper, we present a degeneracy-aware and drift-resilient loop closing method to improve place recognition and resolve 3D location ambiguities for simultaneous localization and mapping (SLAM) in GPS-denied, large-scale and perceptually-degraded environments. More specifically, we focus on SLAM in subterranean environments (e.g., lava tubes, caves, and mines) that represent examples of complex and ambiguous environments where current methods have inadequate performance.

Andrea Tagliabue, Jesus Tordesillas, Xiaoyi Cai et al.

State estimation for robots navigating in GPS-denied and perceptually-degraded environments, such as underground tunnels, mines and planetary subsurface voids, remains challenging in robotics. Towards this goal, we present LION (Lidar-Inertial Observability-Aware Navigator), which is part of the state estimation framework developed by the team CoSTAR for the DARPA Subterranean Challenge, where the team achieved second and first places in the Tunnel and Urban circuits in August 2019 and February 2020, respectively. LION provides high-rate odometry estimates by fusing high-frequency inertial data from an IMU and low-rate relative pose estimates from a lidar via a fixed-lag sliding window smoother. LION does not require knowledge of relative positioning between lidar and IMU, as the extrinsic calibration is estimated online. In addition, LION is able to self-assess its performance using an observability metric that evaluates whether the pose estimate is geometrically ill-constrained. Odometry and confidence estimates are used by HeRO, a supervisory algorithm that provides robust estimates by switching between different odometry sources. In this paper we benchmark the performance of LION in perceptually-degraded subterranean environments, demonstrating its high technology readiness level for deployment in the field.

Hyungho Chris Choi, Inhwan Wee, Micah Corah et al.

Unmanned aerial vehicles are rapidly evolving within the field of robotics. However, their performance is often limited by payload capacity, operational time, and robustness to impact and collision. These limitations of aerial vehicles become more acute for missions in challenging environments such as subterranean structures which may require extended autonomous operation in confined spaces. While software solutions for aerial robots are developing rapidly, improvements to hardware are critical to applying advanced planners and algorithms in large and dangerous environments where the short range and high susceptibility to collisions of most modern aerial robots make applications in realistic subterranean missions infeasible. To provide such hardware capabilities, one needs to design and implement a hardware solution that takes into the account the Size, Weight, and Power (SWaP) constraints. This work focuses on providing a robust and versatile hybrid platform that improves payload capacity, operation time, endurance, and versatility. The Bi-modal Aerial and Terrestrial hybrid vehicle (BAXTER) is a solution that provides two modes of operation, aerial and terrestrial. BAXTER employs two novel hardware mechanisms: the M-Suspension and the Decoupled Transmission which together provide resilience during landing and crashes and efficient terrestrial operation. Extensive flight tests were conducted to characterize the vehicle's capabilities, including robustness and endurance. Additionally, we propose Agile Mode Transfer (AMT), a transition from aerial to terrestrial operation that seeks to minimize impulses during impact to the ground which is a quick and simple transition process that exploits BAXTER's resilience to impact.

Rohan Thakker, Nikhilesh Alatur, David D. Fan et al.

We propose a framework for resilient autonomous navigation in perceptually challenging unknown environments with mobility-stressing elements such as uneven surfaces with rocks and boulders, steep slopes, negative obstacles like cliffs and holes, and narrow passages. Environments are GPS-denied and perceptually-degraded with variable lighting from dark to lit and obscurants (dust, fog, smoke). Lack of prior maps and degraded communication eliminates the possibility of prior or off-board computation or operator intervention. This necessitates real-time on-board computation using noisy sensor data. To address these challenges, we propose a resilient architecture that exploits redundancy and heterogeneity in sensing modalities. Further resilience is achieved by triggering recovery behaviors upon failure. We propose a fast settling algorithm to generate robust multi-fidelity traversability estimates in real-time. The proposed approach was deployed on multiple physical systems including skid-steer and tracked robots, a high-speed RC car and legged robots, as a part of Team CoSTAR's effort to the DARPA Subterranean Challenge, where the team won 2nd and 1st place in the Tunnel and Urban Circuits, respectively.

Kenny Chen, Alexandra Pogue, Brett T. Lopez et al.

Monocular depth inference has gained tremendous attention from researchers in recent years and remains as a promising replacement for expensive time-of-flight sensors, but issues with scale acquisition and implementation overhead still plague these systems. To this end, this work presents an unsupervised learning framework that is able to predict at-scale depth maps and egomotion, in addition to camera intrinsics, from a sequence of monocular images via a single network. Our method incorporates both spatial and temporal geometric constraints to resolve depth and pose scale factors, which are enforced within the supervisory reconstruction loss functions at training time. Only unlabeled stereo sequences are required for training the weights of our single-network architecture, which reduces overall implementation overhead as compared to previous methods. Our results demonstrate strong performance when compared to the current state-of-the-art on multiple sequences of the KITTI driving dataset and can provide faster training times with its reduced network complexity.

Yasin Almalioglu, Angel Santamaria-Navarro, Benjamin Morrell et al.

In recent years, unsupervised deep learning approaches have received significant attention to estimate the depth and visual odometry (VO) from unlabelled monocular image sequences. However, their performance is limited in challenging environments due to perceptual degradation, occlusions and rapid motions. Moreover, the existing unsupervised methods suffer from the lack of scale-consistency constraints across frames, which causes that the VO estimators fail to provide persistent trajectories over long sequences. In this study, we propose an unsupervised monocular deep VO framework that predicts six-degrees-of-freedom pose camera motion and depth map of the scene from unlabelled RGB image sequences. We provide detailed quantitative and qualitative evaluations of the proposed framework on a) a challenging dataset collected during the DARPA Subterranean challenge; and b) the benchmark KITTI and Cityscapes datasets. The proposed approach outperforms both traditional and state-of-the-art unsupervised deep VO methods providing better results for both pose estimation and depth recovery. The presented approach is part of the solution used by the COSTAR team participating at the DARPA Subterranean Challenge.

Amanda Bouman, Muhammad Fadhil Ginting, Nikhilesh Alatur et al.

This paper serves as one of the first efforts to enable large-scale and long-duration autonomy using the Boston Dynamics Spot robot. Motivated by exploring extreme environments, particularly those involved in the DARPA Subterranean Challenge, this paper pushes the boundaries of the state-of-practice in enabling legged robotic systems to accomplish real-world complex missions in relevant scenarios. In particular, we discuss the behaviors and capabilities which emerge from the integration of the autonomy architecture NeBula (Networked Belief-aware Perceptual Autonomy) with next-generation mobility systems. We will discuss the hardware and software challenges, and solutions in mobility, perception, autonomy, and very briefly, wireless networking, as well as lessons learned and future directions. We demonstrate the performance of the proposed solutions on physical systems in real-world scenarios.

David D. Fan, Rohan Thakker, Tara Bartlett et al.

Hybrid ground and aerial vehicles can possess distinct advantages over ground-only or flight-only designs in terms of energy savings and increased mobility. In this work we outline our unified framework for controls, planning, and autonomy of hybrid ground/air vehicles. Our contribution is three-fold: 1) We develop a control scheme for the control of passive two-wheeled hybrid ground/aerial vehicles. 2) We present a unified planner for both rolling and flying by leveraging differential flatness mappings. 3) We conduct experiments leveraging mapping and global planning for hybrid mobility in unknown environments, showing that hybrid mobility uses up to five times less energy than flying only.

Angel Santamaria-Navarro, Rohan Thakker, David D. Fan et al.

Robots and particularly drones are especially useful in exploring extreme environments that pose hazards to humans. To ensure safe operations in these situations, usually perceptually degraded and without good GNSS, it is critical to have a reliable and robust state estimation solution. The main body of literature in robot state estimation focuses on developing complex algorithms favoring accuracy. Typically, these approaches rely on a strong underlying assumption: the main estimation engine will not fail during operation. In contrast, we propose an architecture that pursues robustness in state estimation by considering redundancy and heterogeneity in both sensing and estimation algorithms. The architecture is designed to expect and detect failures and adapt the behavior of the system to ensure safety. To this end, we present HeRO (Heterogeneous Redundant Odometry): a stack of estimation algorithms running in parallel supervised by a resiliency logic. This logic carries out three main functions: a) perform confidence tests both in data quality and algorithm health; b) re-initialize those algorithms that might be malfunctioning; c) generate a smooth state estimate by multiplexing the inputs based on their quality. The state and quality estimates are used by the guidance and control modules to adapt the mobility behaviors of the system. The validation and utility of the approach are shown with real experiments on a flying robot for the use case of autonomous exploration of subterranean environments, with particular results from the STIX event of the DARPA Subterranean Challenge.

Takahiro Sasaki, Kyohei Otsu, Rohan Thakker et al.

In addition to conventional ground rovers, the Mars 2020 mission will send a helicopter to Mars. The copter's high-resolution data helps the rover to identify small hazards such as steps and pointy rocks, as well as providing rich textual information useful to predict perception performance. In this paper, we consider a three-agent system composed of a Mars rover, copter, and orbiter. The objective is to provide good localization to the rover by selecting an optimal path that minimizes the localization uncertainty accumulation during the rover's traverse. To achieve this goal, we quantify the localizability as a goodness measure associated with the map, and conduct a joint-space search over rover's path and copter's perceptual actions given prior information from the orbiter. We jointly address where to map by the copter and where to drive by the rover using the proposed iterative copter-rover path planner. We conducted numerical simulations using the map of Mars 2020 landing site to demonstrate the effectiveness of the proposed planner.

Björn Lindqvist, Sina Sharif Mansouri, Ali-akbar Agha-mohammadi et al.

This article proposes a Novel Nonlinear Model Predictive Control (NMPC) for navigation and obstacle avoidance of an Unmanned Aerial Vehicle (UAV). The proposed NMPC formulation allows for a fully parametric obstacle trajectory, while in this article we apply a classification scheme to differentiate between different kinds of trajectories to predict future obstacle positions. The trajectory calculation is done from an initial condition, and fed to the NMPC as an additional input. The solver used is the nonlinear, non-convex solver Proximal Averaged Newton for Optimal Control (PANOC) and its associated software OpEn (Optimization Engine), in which we apply a penalty method to properly consider the obstacles and other constraints during navigation. The proposed NMPC scheme allows for real-time solutions using a sampling time of 50 ms and a two second prediction of both the obstacle trajectory and the NMPC problem, which implies that the scheme can be considered as a local path-planner. This paper will present the NMPC cost function and constraint formulation, as well as the methodology of dealing with the dynamic obstacles. We include multiple laboratory experiments to demonstrate the efficacy of the proposed control architecture, and to show that the proposed method delivers fast and computationally stable solutions to the dynamic obstacle avoidance scenarios.

Sina Sharif Mansouri, Christoforos Kanellakis, Bjorn Lindqvist et al.

This article proposes a novel Nonlinear Model Predictive Control (NMPC) framework for Micro Aerial Vehicle (MAV) autonomous navigation in constrained environments. The introduced framework allows us to consider the nonlinear dynamics of MAVs and guarantees real-time performance. Our first contribution is to design a computationally efficient subspace clustering method to reveal from geometrical constraints to underlying constraint planes within a 3D point cloud, obtained from a 3D lidar scanner. The second contribution of our work is to incorporate the extracted information into the nonlinear constraints of NMPC for avoiding collisions. Our third contribution focuses on making the controller robust by considering the uncertainty of localization and NMPC using the Shannon entropy. This step enables us to track either the position or velocity references, or none of them if necessary. As a result, the collision avoidance constraints are defined in the local coordinates of MAVs and it remains active and guarantees collision avoidance, despite localization uncertainties, e.g., position estimation drifts. Additionally, as the platform continues the mission, this will result in less uncertain position estimations, due to the feature extraction and loop closure. The efficacy of the suggested framework has been evaluated using various simulations in the Gazebo environment.

Ali-akbar Agha-mohammadi, Eric Heiden, Karol Hausman et al.

Representing the environment is a fundamental task in enabling robots to act autonomously in unknown environments. In this work, we present confidence-rich mapping (CRM), a new algorithm for spatial grid-based mapping of the 3D environment. CRM augments the occupancy level at each voxel by its confidence value. By explicitly storing and evolving confidence values using the CRM filter, CRM extends traditional grid mapping in three ways: first, it partially maintains the probabilistic dependence among voxels. Second, it relaxes the need for hand-engineering an inverse sensor model and proposes the concept of sensor cause model that can be derived in a principled manner from the forward sensor model. Third, and most importantly, it provides consistent confidence values over the occupancy estimation that can be reliably used in collision risk evaluation and motion planning. CRM runs online and enables mapping environments where voxels might be partially occupied. We demonstrate the performance of the method on various datasets and environments in simulation and on physical systems. We show in real-world experiments that, in addition to achieving maps that are more accurate than traditional methods, the proposed filtering scheme demonstrates a much higher level of consistency between its error and the reported confidence, hence, enabling a more reliable collision risk evaluation for motion planning.

Sina Sharif Mansouri, Farhad Pourkamali-Anaraki, Miguel Castano Arranz et al.

This article proposes a novel unsupervised learning framework for detecting the number of tunnel junctions in subterranean environments based on acquired 2D point clouds. The implementation of the framework provides valuable information for high level mission planners to navigate an aerial platform in unknown areas or robot homing missions. The framework utilizes spectral clustering, which is capable of uncovering hidden structures from connected data points lying on non-linear manifolds. The spectral clustering algorithm computes a spectral embedding of the original 2D point cloud by utilizing the eigen decomposition of a matrix that is derived from the pairwise similarities of these points. We validate the developed framework using multiple data-sets, collected from multiple realistic simulations, as well as from real flights in underground environments, demonstrating the performance and merits of the proposed methodology.

Ali-akbar Agha-mohammadi, Andrea Tagliabue, Stephanie Schneider et al.

In this report for the Nasa NIAC Phase I study, we present a mission architecture and a robotic platform, the Shapeshifter, that allow multi-domain and redundant mobility on Saturn's moon Titan, and potentially other bodies with atmospheres. The Shapeshifter is a collection of simple and affordable robotic units, called Cobots, comparable to personal palm-size quadcopters. By attaching and detaching with each other, multiple Cobots can shape-shift into novel structures, capable of (a) rolling on the surface, to increase the traverse range, (b) flying in a flight array formation, and (c) swimming on or under liquid. A ground station complements the robotic platform, hosting science instrumentation and providing power to recharge the batteries of the Cobots. Our Phase I study had the objective of providing an initial assessment of the feasibility of the proposed robotic platform architecture, and in particular (a) to characterize the expected science return of a mission to the Sotra-Patera region on Titan; (b) to verify the mechanical and algorithmic feasibility of building a multi-agent platform capable of flying, docking, rolling and un-docking; (c) to evaluate the increased range and efficiency of rolling on Titan w.r.t to flying; (d) to define a case-study of a mission for the exploration of the cryovolcano Sotra-Patera on Titan, whose expected variety of geological features challenges conventional mobility platforms.

Kamak Ebadi, Yun Chang, Matteo Palieri et al.

Simultaneous Localization and Mapping (SLAM) in large-scale, unknown, and complex subterranean environments is a challenging problem. Sensors must operate in off-nominal conditions; uneven and slippery terrains make wheel odometry inaccurate, while long corridors without salient features make exteroceptive sensing ambiguous and prone to drift; finally, spurious loop closures that are frequent in environments with repetitive appearance, such as tunnels and mines, could result in a significant distortion of the entire map. These challenges are in stark contrast with the need to build highly-accurate 3D maps to support a wide variety of applications, ranging from disaster response to the exploration of underground extraterrestrial worlds. This paper reports on the implementation and testing of a lidar-based multi-robot SLAM system developed in the context of the DARPA Subterranean Challenge. We present a system architecture to enhance subterranean operation, including an accurate lidar-based front-end, and a flexible and robust back-end that automatically rejects outlying loop closures. We present an extensive evaluation in large-scale, challenging subterranean environments, including the results obtained in the Tunnel Circuit of the DARPA Subterranean Challenge. Finally, we discuss potential improvements, limitations of the state of the art, and future research directions.

David D. Fan, Ali-akbar Agha-mohammadi, Evangelos A. Theodorou

Learning-based control aims to construct models of a system to use for planning or trajectory optimization, e.g. in model-based reinforcement learning. In order to obtain guarantees of safety in this context, uncertainty must be accurately quantified. This uncertainty may come from errors in learning (due to a lack of data, for example), or may be inherent to the system. Propagating uncertainty forward in learned dynamics models is a difficult problem. In this work we use deep learning to obtain expressive and flexible models of how distributions of trajectories behave, which we then use for nonlinear Model Predictive Control (MPC). We introduce a deep quantile regression framework for control that enforces probabilistic quantile bounds and quantifies epistemic uncertainty. Using our method we explore three different approaches for learning tubes that contain the possible trajectories of the system, and demonstrate how to use each of them in a Tube MPC scheme. We prove these schemes are recursively feasible and satisfy constraints with a desired margin of probability. We present experiments in simulation on a nonlinear quadrotor system, demonstrating the practical efficacy of these ideas.

Andrea Tagliabue, Stephanie Schneider, Marco Pavone et al.

In this paper we present a mission architecture and a robotic platform, the Shapeshifter, that allow multi-domain and redundant mobility on Saturn's moon Titan, and potentially other bodies with atmospheres. The Shapeshifter is a collection of simple and affordable robotic units, called Cobots, comparable to personal palm-size quadcopters. By attaching and detaching with each other, multiple Cobots can shape-shift into novel structures, capable of (a) rolling on the surface, to increase the traverse range, (b) flying in a flight array formation, and (c) swimming on or under liquid. A ground station complements the robotic platform, hosting science instrumentation and providing power to recharge the batteries of the Cobots. In the first part of this paper we experimentally show the flying, docking and rolling capabilities of a Shapeshifter constituted by two Cobots, presenting ad-hoc control algorithms. We additionally evaluate the energy-efficiency of the rolling-based mobility strategy by deriving an analytic model of the power consumption and by integrating it in a high-fidelity simulation environment. In the second part we tailor our mission architecture to the exploration of Titan. We show that the properties of the Shapeshifter allow the exploration of the possible cryovolcano Sotra Patera, Titan's Mare and canyons.

Jared Strader, Kyohei Otsu, Ali-akbar Agha-mohammadi

Highly accurate real-time localization is of fundamental importance for the safety and efficiency of planetary rovers exploring the surface of Mars. Mars rover operations rely on vision-based systems to avoid hazards as well as plan safe routes. However, vision-based systems operate on the assumption that sufficient visual texture is visible in the scene. This poses a challenge for vision-based navigation on Mars where regions lacking visual texture are prevalent. To overcome this, we make use of the ability of the rover to actively steer the visual sensor to improve fault tolerance and maximize the perception performance. This paper answers the question of where and when to look by presenting a method for predicting the sensor trajectory that maximizes the localization performance of the rover. This is accomplished by an online assessment of possible trajectories using synthetic, future camera views created from previous observations of the scene. The proposed trajectories are quantified and chosen based on the expected localization performance. In this work, we validate the proposed method in field experiments at the Jet Propulsion Laboratory (JPL) Mars Yard. Furthermore, multiple performance metrics are identified and evaluated for reducing the overall runtime of the algorithm. We show how actively steering the perception system increases the localization accuracy compared to traditional fixed-sensor configurations.

David D. Fan, Jennifer Nguyen, Rohan Thakker et al.

Deep learning has enjoyed much recent success, and applying state-of-the-art model learning methods to controls is an exciting prospect. However, there is a strong reluctance to use these methods on safety-critical systems, which have constraints on safety, stability, and real-time performance. We propose a framework which satisfies these constraints while allowing the use of deep neural networks for learning model uncertainties. Central to our method is the use of Bayesian model learning, which provides an avenue for maintaining appropriate degrees of caution in the face of the unknown. In the proposed approach, we develop an adaptive control framework leveraging the theory of stochastic CLFs (Control Lyapunov Functions) and stochastic CBFs (Control Barrier Functions) along with tractable Bayesian model learning via Gaussian Processes or Bayesian neural networks. Under reasonable assumptions, we guarantee stability and safety while adapting to unknown dynamics with probability 1. We demonstrate this architecture for high-speed terrestrial mobility targeting potential applications in safety-critical high-speed Mars rover missions.

Thomas Lew, Tomoki Emmei, David D. Fan et al.

Autonomous exploration of unknown environments with aerial vehicles remains a challenge, especially in perceptually degraded conditions. Dust, fog, or a lack of visual or LiDAR-based features results in severe difficulties for state estimation algorithms, which failure can be catastrophic. In this work, we show that it is indeed possible to navigate in such conditions without any exteroceptive sensing by exploiting collisions instead of treating them as constraints. To this end, we present a novel contact-based inertial odometry (CIO) algorithm: it uses estimated external forces with the environment to detect collisions and generate pseudo-measurements of the robot velocity, enabling autonomous flight. To fully exploit this method, we first perform modeling of a hybrid ground and aerial vehicle which can withstand collisions at moderate speeds, for which we develop an external wrench estimation algorithm. Then, we present our CIO algorithm and develop a reactive planner and control law which encourage exploration by bouncing off obstacles. All components of this framework are validated in hardware experiments and we demonstrate that a quadrotor can traverse a cluttered environment using an IMU only. This work can be used on drones to recover from visual inertial odometry failure or on micro-drones that do not have the payload capacity to carry cameras, LiDARs or powerful computers.

Sung-Kyun Kim, Rohan Thakker, Ali-akbar Agha-mohammadi

Decision-making under uncertainty is a crucial ability for autonomous systems. In its most general form, this problem can be formulated as a Partially Observable Markov Decision Process (POMDP). The solution policy of a POMDP can be implicitly encoded as a value function. In partially observable settings, the value function is typically learned via forward simulation of the system evolution. Focusing on accurate and long-range risk assessment, we propose a novel method, where the value function is learned in different phases via a bi-directional search in belief space. A backward value learning process provides a long-range and risk-aware base policy. A forward value learning process ensures local optimality and updates the policy via forward simulations. We consider a class of scalable and continuous-space rover navigation problems (RNP) to assess the safety, scalability, and optimality of the proposed algorithm. The results demonstrate the capabilities of the proposed algorithm in evaluating long-range risk/safety of the planner while addressing continuous problems with long planning horizons.

Ali-akbar Agha-mohammadi

Occupancy grids are the most common framework when it comes to creating a map of the environment using a robot. This paper studies occupancy grids from the motion planning perspective and proposes a mapping method that provides richer data (map) for the purpose of planning and collision avoidance. Typically, in occupancy grid mapping, each cell contains a single number representing the probability of cell being occupied. This leads to conflicts in the map, and more importantly inconsistency between the map error and reported confidence values. Such inconsistencies pose challenges for the planner that relies on the generated map for planning motions. In this work, we store a richer data at each voxel including an accurate estimate of the variance of occupancy. We show that in addition to achieving maps that are often more accurate than tradition methods, the proposed filtering scheme demonstrates a much higher level of consistency between its error and its reported confidence. This allows the planner to reason about acquisition of the future sensory information. Such planning can lead to active perception maneuvers that while guiding the robot toward the goal aims at increasing the confidence in parts of the map that are relevant to accomplishing the task.

Brian Ichter, Edward Schmerling, Ali-akbar Agha-mohammadi et al.

In this paper we present the PUMP (Parallel Uncertainty-aware Multiobjective Planning) algorithm for addressing the stochastic kinodynamic motion planning problem, whereby one seeks a low-cost, dynamically-feasible motion plan subject to a constraint on collision probability (CP). To ensure exhaustive evaluation of candidate motion plans (as needed to tradeoff the competing objectives of performance and safety), PUMP incrementally builds the Pareto front of the problem, accounting for the optimization objective and an approximation of CP. This is performed by a massively parallel multiobjective search, here implemented with a focus on GPUs. Upon termination of the exploration phase, PUMP searches the Pareto set of motion plans to identify the lowest cost solution that is certified to satisfy the CP constraint (according to an asymptotically exact estimator). We introduce a novel particle-based CP approximation scheme, designed for efficient GPU implementation, which accounts for dependencies over the history of a trajectory execution. We present numerical experiments for quadrotor planning wherein PUMP identifies solutions in ~100 ms, evaluating over one hundred thousand partial plans through the course of its exploration phase. The results show that this multiobjective search achieves a lower motion plan cost, for the same CP constraint, compared to a safety buffer-based search heuristic and repeated RRT trials.

Ali-akbar Agha-mohammadi, Saurav Agarwal, Sung-Kyun Kim et al.

Simultaneous localization and Planning (SLAP) is a crucial ability for an autonomous robot operating under uncertainty. In its most general form, SLAP induces a continuous POMDP (partially-observable Markov decision process), which needs to be repeatedly solved online. This paper addresses this problem and proposes a dynamic replanning scheme in belief space. The underlying POMDP, which is continuous in state, action, and observation space, is approximated offline via sampling-based methods, but operates in a replanning loop online to admit local improvements to the coarse offline policy. This construct enables the proposed method to combat changing environments and large localization errors, even when the change alters the homotopy class of the optimal trajectory. It further outperforms the state-of-the-art FIRM (Feedback-based Information RoadMap) method by eliminating unnecessary stabilization steps. Applying belief space planning to physical systems brings with it a plethora of challenges. A key focus of this paper is to implement the proposed planner on a physical robot and show the SLAP solution performance under uncertainty, in changing environments and in the presence of large disturbances, such as a kidnapped robot situation.

Beipeng Mu, Matthew Giamou, Liam Paull et al.

Active SLAM is the task of actively planning robot paths while simultaneously building a map and localizing within. Existing work has focused on planning paths with occupancy grid maps, which do not scale well and suffer from long term drift. This work proposes a Topological Feature Graph (TFG) representation that scales well and develops an active SLAM algorithm with it. The TFG uses graphical models, which utilize independences between variables, and enables a unified quantification of exploration and exploitation gains with a single entropy metric. Hence, it facilitates a natural and principled balance between map exploration and refinement. A probabilistic roadmap path-planner is used to generate robot paths in real time. Experimental results demonstrate that the proposed approach achieves better accuracy than a standard grid-map based approach while requiring orders of magnitude less computation and memory resources.

Shayegan Omidshafiei, Ali-akbar Agha-mohammadi, Christopher Amato et al.

The focus of this paper is on solving multi-robot planning problems in continuous spaces with partial observability. Decentralized partially observable Markov decision processes (Dec-POMDPs) are general models for multi-robot coordination problems, but representing and solving Dec-POMDPs is often intractable for large problems. To allow for a high-level representation that is natural for multi-robot problems and scalable to large discrete and continuous problems, this paper extends the Dec-POMDP model to the decentralized partially observable semi-Markov decision process (Dec-POSMDP). The Dec-POSMDP formulation allows asynchronous decision-making by the robots, which is crucial in multi-robot domains. We also present an algorithm for solving this Dec-POSMDP which is much more scalable than previous methods since it can incorporate closed-loop belief space macro-actions in planning. These macro-actions are automatically constructed to produce robust solutions. The proposed method's performance is evaluated on a complex multi-robot package delivery problem under uncertainty, showing that our approach can naturally represent multi-robot problems and provide high-quality solutions for large-scale problems.