Authors: Basant Sharma (University of Tartu); Arun Singh (Tampere University of Technology, Hydraulics and Automation); Madhava Krishna (IIIT Hyderabad); Aditya Sharma (IIIT Hyderabad)
Abstract: Safe autonomous driving critically depends on how well the ego-vehicle can predict the trajectories of neighbouring vehicles. To this end, several trajectory prediction algorithms have been presented in the existing literature which outputs a multi-modal distribution of obstacle trajectories instead of a single deterministic prediction to account for the underlying uncertainty. However, existing planners cannot handle the multi-modality based on just sample-level information of the predictions.
With this motivation, this paper proposes a trajectory optimizer that can leverage the distributional aspects of an arbitrarily complex distribution, in particular, an output distribution represented as a deep neural network, in a computationally tractable and sample-efficient manner. The core of our approach is built on embedding distribution in Reproducing Kernel Hilbert Space (RKHS) , which we leverage in two ways. First, we propose an RKHS embedding approach to select probable samples from the obstacle trajectory distribution. Second, we rephrase chance-constrained optimization as distribution matching in RKHS and propose a novel sampling-based optimizer for its solution.
Authors: Wonsuhk Jung (Georgia Institute of Technology); Long Kiu Chung (Georgia Institute of Technology); Srivatsank Pullabhotla (Georgia Institute of Technology); Parth Shinde (Georgia Institute of Technology); Shreyas Kousik (Georgia Institute of Technology)
Abstract: This paper proposes an approach for solving a reach-avoid motion planning problem given a mobile robot with black-box dynamics. We consider the specific case where obstacles are near the robot’s goal, causing a near danger (i.e., narrow gap) scenario. We apply neural networks to learn a space of motion plans, which the robot tracks with a feedback controller. This results in a lumped type of uncertainty that we call tracking error to represent the fact that the robot cannot perfectly track any plan. We show how our recent work on Piecewise Affine Reachability Computation (PARC) combines elegantly with feedforward, rectified linear unit (ReLU)-activated neural network planners to discover safe, goal-reaching trajectories near danger. For this short paper, we demonstrate the approach on a 2-D double integrator as a preliminary example.
Authors: Jean-Baptiste Bouvier (University of California Berkeley)
Abstract: In this paper, we seek to learn a robot policy guaranteed to satisfy state constraints. Typical RL algorithms only encourage constraint satisfaction through reward shaping. However, such soft constraints cannot offer safety guarantees. To address this gap, we propose POLICEd RL, a novel RL algorithm explicitly designed to enforce affine hard constraints in closed-loop with a black-box environment. Our key insight is to make the learned policy be affine around the unsafe set and to use this affine region as a repulsive buffer to prevent trajectories from violating the constraint. We prove that such policies guarantee constraint satisfaction. Our results demonstrate the capacity of POLICEd RL to enforce hard constraints in robotic tasks while significantly outperforming existing methods.
Authors: Zixu Zhang (Princeton University); Haimin Hu (Princeton University); Kensuke Nakamura (Carnegie Mellon University); Andrea Bajcsy (Carnegie Mellon University); Jaime F Fisac (Princeton University)
Abstract: An outstanding challenge for robotic systems like autonomous vehicles is ensuring safe interaction with humans without sacrificing performance. Existing safety methods often neglect the robot’s ability to learn and adapt at runtime, leading to overly conservative behavior. This paper proposes a new closed-loop paradigm for synthesizing safe control policies that explicitly account for the robot’s evolving uncertainty and its ability to quickly respond to future scenarios as they arise, by jointly considering the physical dynamics and the robot’s learning algorithm. We leverage adversarial reinforcement learning for tractable safety analysis under high-dimensional learning dynamics and demonstrate our framework’s ability to work with both Bayesian belief propagation and implicit learning through large pre-trained neural trajectory predictors.
Authors: Ismail Geles (University of Zurich); Leonard Bauersfeld (University of Zurich); Angel Romero (University of Zurich); Jiaxu Xing (University of Zurich); Davide Scaramuzza (University of Zurich)
Abstract: Quadrotors are among the most agile flying robots. Despite recent advances in learning-based control and computer vision, autonomous drones still rely on explicit state estimation. On the other hand, human pilots only rely on a first-person-view video stream from the drone onboard camera to push the platform to its limits and fly robustly in unseen environments. To the best of our knowledge, we present the first vision-based quadrotor system that autonomously navigates through a sequence of gates at high speeds while directly mapping pixels to control commands. Like professional drone-racing pilots, our system does not use explicit state estimation and leverages the same control commands humans use (collective thrust and body rates). We demonstrate agile flight at speeds up to 40km/h with accelerations up to 2g. This is achieved by training vision-based policies with reinforcement learning (RL). The training is facilitated using an asymmetric actor-critic with access to privileged information. To overcome the computational complexity during image-based RL training, we use the inner edges of the gates as a sensor abstraction. This simple yet robust, task-relevant representation can be simulated during training without rendering images. During deployment, a Swin-transformer-based gate detector is used. Our approach enables autonomous agile flight with standard, off-the-shelf hardware. Although our demonstration focuses on drone racing, we believe that our method has an impact beyond drone racing and can serve as a foundation for future research into real-world applications in structured environments.
Authors: Roee M Francos (Technion-IIT)
Abstract: We address the problem of large-scale traffic management for autonomous vehicles. We derive a safety risk prediction framework for autonomous vehicle interactions at road intersections using Graph Neural Networks (GNN) as well as a unique “traffic signal” control plan for each intersection. The plan controls the status and duration of the traffic lights at road intersections while addressing the safety implications of the chosen plan.
Initially, due to existing limitations on the availability of Urban Air Mobility (UAM) vehicle trajectory datasets, we develop safe traffic control algorithms for autonomous vehicle interactions based on both simulation and real-world data obtained from ground vehicles, applicable to traffic management of autonomous ground vehicles. Next, we present an approach that adapts the obtained results to scenarios involving electrical vertical takeoff and landing vehicles (eVTOLs) for aerial transportation in urban areas by extending the concept of 2 dimensional highways into a 2.5-dimensional air-highway network on which vehicles travel.
To the best of our knowledge, we propose the first framework that integrates both safety constraints as well as adaptive traffic signal control reinforcement learning based protocols for safe and efficient movement coordination on air highways.
Authors: Anushri Dixit (Princeton University); Zhiting Mei (Princeton University)*; Meghan Booker (Princeton University); Mariko Storey-Matsutani (Princeton University); Allen Z. Ren (Princeton University); Anirudha Majumdar (Princeton University)
Abstract: Rapid advances in perception have enabled large pre-trained models to be used out of the box for transforming high-dimensional, noisy, and partial observations of the world into rich occupancy representations. However, the reliability of these models and consequently their safe integration onto robots remains unknown when deployed in environments unseen during training. In this work, we address this challenge by rigorously quantifying the uncertainty of pre-trained perception systems for object detection via a novel calibration technique based on conformal prediction. As a result, the calibrated perception system can be used in combination with any safe planner to provide an end-to-end statistical assurance on safety in unseen environments. We evaluate the resulting approach, Perceive with Confidence (PwC), with experiments in simulation and on hardware where a quadruped robot navigates through previously unseen indoor, static environments. These experiments validate the safety assurances for obstacle avoidance provided by PwC and demonstrate up to 40% improvements in empirical safety compared to baselines. Videos and code can be found at https://perceive-with-confidence.github.io.
Authors: Jay Patrikar (Carnegie Mellon University); Sushant Veer (NVIDIA Research); Apoorva Sharma (NVIDIA Research); Marco Pavone (NVIDIA); Sebastian Scherer (Carnegie Mellon University)
Abstract: Modern neural trajectory predictors in autonomous driving are developed using imitation learning (IL) from driving logs. Although IL benefits from its ability to glean nuanced and multi-modal human driving behaviors from large datasets, the resulting predictors often struggle with out-of-distribution (OOD) scenarios and with traffic rule compliance. On the other hand, classical rule-based predictors, by design, can predict traffic rule satisfying behaviors while being robust to OOD scenarios, but these predictors fail to capture nuances in agent-to-agent interactions and human driver's intent. In this paper, we present RuleFuser, a posterior-net inspired evidential framework that combines neural predictors with classical rule-based predictors to draw on the complementary benefits of both, thereby striking a balance between performance and traffic rule compliance. The efficacy of our approach is demonstrated on the real-world nuPlan dataset where RuleFuser leverages the higher performance of the neural predictor in in-distribution (ID) scenarios and the higher safety offered by the rule-based predictor in OOD scenarios.
Authors: Tairan He (Carnegie Mellon University); Chong Zhang (ETH Zurich); Wenli Xiao (Carnegie Mellon University); Guanqi He (Carnegie Mellon University); Changliu Liu (Carnegie Mellon University); Guanya Shi (Carnegie Mellon University)
Abstract: Legged robots navigating cluttered environments must be jointly agile for efficient task execution and safe to avoid collisions with obstacles or humans. Existing studies either develop conservative controllers (< 1.0 m/s) to ensure safety, or focus on agility without considering potentially fatal collisions. This paper introduces Agile But Safe (ABS), a learning-based control framework that enables agile and collision-free locomotion for quadrupedal robots. ABS involves an agile policy to execute agile motor skills amidst obstacles and a recovery policy to prevent failures, collaboratively achieving high-speed and collision-free navigation. The policy switch in ABS is governed by a learned control-theoretic reach-avoid value network, which also guides the recovery policy as an objective function, thereby safeguarding the robot in a closed loop. The training process involves the learning of the agile policy, the reach-avoid value network, the recovery policy, and an exteroception representation network, all in simulation. These trained modules can be directly deployed in the real world with onboard sensing and computation, leading to high-speed and collision-free navigation in confined indoor and outdoor spaces with both static and dynamic obstacles.
Authors: Christopher G Agia (Stanford University); Rohan Sinha (Stanford University); Jingyun Yang (Stanford University); Ziang Cao (Stanford University); Rika Antonova (Stanford University); Marco Pavone (Stanford University); Jeannette Bohg (Stanford)
Abstract: Robot behavior policies trained via imitation learning are prone to failure under conditions that deviate from their training data. Thus, algorithms that monitor learned policies at test time and provide early warnings of failure are necessary to facilitate scalable deployment. We propose a runtime monitoring framework that splits the detection of failures into two complementary categories: 1) Erratic failures, which we propose to detect using a statistical measure of temporal action consistency, and 2) task progression failures, where we use VLMs to detect when the policy confidently and consistently takes actions that do not solve the task. Our approach has two key strengths. First, because learned policies exhibit diverse failure modes, combining complementary detectors leads to significantly higher accuracy at failure detection. Second, using a statistical temporal action consistency measure ensures that we quickly detect when multi- modal, generative policies exhibit erratic behavior at negligible computation cost. In contrast, we only use VLMs to detect failure modes that are less time-sensitive. We demonstrate our approach in the context of diffusion policies trained on a multi-modal domain and simulated bi-manual robotic manipulation domains. The resultant system, unifying temporal consistency detection with VLM runtime monitoring, detects 15% more failures than using either of the two detectors, thus highlighting the importance of assigning specialized detectors to complementary categories of failure.
Authors: Lujie Yang (Massachusetts Institute of Technology); Hongkai Dai (Toyota Research Institute); Zhouxing Shi (UCLA); Cho-Jui Hsieh (UCLA); Russ Tedrake (MIT); Huan Zhang (UIUC)
Abstract: Learning-based neural network (NN) control policies have shown impressive empirical performance in a wide range of tasks in robotics and control. However, formal (Lyapunov) stability guarantees over the region-of-attraction (ROA) for NN controllers with nonlinear dynamical systems are challenging to obtain, and most existing approaches rely on expensive solvers such as sums-of-squares (SOS), mixed-integer programming (MIP), or satisfiability modulo theories (SMT). In this paper, we demonstrate a new framework for learning NN controllers together with Lyapunov certificates using fast empirical falsification and strategic regularizations. We propose a novel formulation that defines a larger verifiable region-of-attraction (ROA) than shown in the literature, and refines the conventional restrictive constraints on Lyapunov derivatives to focus only on certifiable ROAs. The Lyapunov condition is rigorously verified post-hoc using branch-and-bound with scalable linear bound propagation-based NN verification techniques. The approach is efficient and flexible, and the full training and verification procedure is accelerated on GPUs without relying on expensive solvers for SOS, MIP, nor SMT. The flexibility and efficiency of our framework allow us to demonstrate Lyapunov-stable output feedback control with synthesized NN-based controllers and NN-based observers with formal stability guarantees, for the first time in literature.
Authors: Frederike Duembgen (University of Toronto); Connor Holmes (University of Toronto); Tim Barfoot (University of Toronto)
Abstract: We provide a concise overview of our progress in identifying and certifying globally optimal solutions of state estimation problems in robotics. We give a summary of the theoretical background, providing pointers for novices in the field to learn about this topic. We then given an overview of the problems we have treated, putting them in a unified framework to make it easier to find, compare, and build upon them. We discuss our methods for simplifying the generation and analysis of these solutions, and finally, present advances to allow to embed them in real-world robotics pipelines. We conclude with a discussion of important open research problems.
Authors: Puze Liu (TU Darmstadt); Jonas Günster (TU Darmstadt); Jan Peters (TU Darmstadt); Davide Tateo (Technische Universität Darmstadt)
Abstract: Ensuring safety for learning-based techniques, especially reinforcement learning, is a critical step toward deploying robot learning in the real world. This problem poses several challenges, such as deriving safety policies from given constraints, tackling challenges in dynamic environments, designing constraints that consider long-term safety, and addressing uncertainty. ATACOM attempts to construct a Constraint Manifold and a safe action space tangent to this manifold, exploiting the prior knowledge of robot dynamics and differentiable constraints. This paper provides an overview of the ATACOM method of handling various types of constraints, including learnable ones. We show that ATACOM effectively incorporates prior knowledge into learning-based methods to solve high-dimensional tasks with complex constraints.
Authors: Alan Papalia (MIT); Yulun Tian (MIT); Jonathan How (MIT); David M Rosen (Northeastern University); John Leonard (MIT)
Abstract: This paper presents an overview of the Burer-Monteiro method (BM), a technique that has been applied to solve robot perception problems to certifiable optimality in real-time. BM is often used to solve semidefinite programming relaxations, which can be used to perform global optimization for non-convex perception problems. Specifically, BM leverages the low-rank structure of typical semidefinite programs to dramatically reduce the computational cost of performing optimization. This paper discusses BM in certifiable perception, with three main objectives: (i) to consolidate information from the literature into a unified presentation, (ii) to elucidate the role of the linear independence constraint qualification (LICQ), a concept not yet well-covered in certifiable perception literature, and (iii) to share practical considerations that are discussed among practitioners but not thoroughly covered in the literature. Our general aim is to offer a practical primer for applying BM towards certifiable perception.
Authors: Hardik Parwana (Toyota Motor North America); Mitchell Black (Toyota Motor North America); Georgios Fainekos (Toyota NA R&D); Bardh Hoxha (Toyota Motor North America); Hideki Okamoto (Toyota Motor North America); Danil Prokhorov (Toyota Research Institute)
Abstract: The rapid advancement of robotics necessitates robust tools for developing and testing safe control architectures in dynamic and uncertain environments. Ensuring safety and reliability in robotics, especially in safety-critical applications, is crucial, driving substantial industrial and academic efforts. In this context, we extend CBFkit, a Python/ROS2 toolbox, which now incorporates a planner using reach-avoid specifications as a cost function. This integration with the Model Predictive Path Integral (MPPI) controllers enables the toolbox to satisfy complex tasks while ensuring formal safety guarantees under various sources of uncertainty using Control Barrier Functions (CBFs). CBFkit is optimized for speed using JAX for automatic differentiation and jaxopt for quadratic program solving. The toolbox supports various robotic applications, including autonomous navigation, human-robot interaction, and multi-robot coordination. The toolbox also offers a comprehensive library of planner, controller, sensor and estimator implementations. Through a series of examples, we demonstrate the enhanced capabilities of CBFkit in different robotic scenarios.
Authors: Javier Borquez (University Of Southern California); Shuang Peng (University Of Southern California); Yiyu Chen (University of Southern California); Quan Nguyen (USC); Somil Bansal (University of Southern California)
Abstract: In this work, we address extending classical Hamilton-Jacobi (HJ) reachability analysis to hybrid dynamical systems. We characterize the reachable sets for hybrid systems through a generalized value function defined over discrete and continuous states of the hybrid system. We also provide a numerical algorithm to compute this value function and obtain the reachable set.
Our framework can compute reachable sets for hybrid systems consisting of multiple discrete modes, each with its own set of nonlinear continuous dynamics, discrete transitions that can be directly commanded or forced by a discrete control input, while still accounting for control bounds and adversarial disturbances in the state evolution. Along with the reachable set, the proposed framework also provides an optimal continuous and discrete controller to ensure system safety. We demonstrate our framework in several simulation case studies, as well as on a real-world testbed.
Authors: Shucheng Kang (Harvard University); Xiaoyang Xu (UCSB); Jay Sarva (Brown University); Ling Liang (University of Maryland at College Park); Heng Yang (Harvard University)
Abstract: We propose semidefinite trajectory optimization (STROM), a framework that computes fast and certifiably optimal solutions for nonconvex trajectory optimization problems defined by polynomial objectives and constraints. STROM employs sparse second-order Lasserre's hierarchy to generate semidefinite program (SDP) relaxations of trajectory optimization. Different from existing tools (e.g., YALMIP and SOSTOOLS in Matlab), STROM generates chain-like multiple-block SDPs with only positive semidefinite (PSD) variables. Moreover, STROM does so two orders of magnitude faster. Underpinning STROM is cuADMM, the first ADMM-based SDP solver implemented in CUDA and runs in GPUs. cuADMM builds upon the symmetric Gauss-Seidel ADMM algorithm and leverages GPU parallelization to speedup solving sparse linear systems and projecting onto PSD cones. In five trajectory optimization problems (inverted pendulum, cart pole, vehicle landing, flying robot, and car back-in), cuADMM computes optimal trajectories (with certified suboptimality below 1%) in minutes (when other solvers take hours or run out of memory) and seconds (when others take minutes). Further, when warmstarted by data-driven initialization in the inverted pendulum problem, cuADMM delivers real-time performance: providing certifiably optimal trajectories in 0.66 seconds despite the SDP has 49,500 variables and 47,351 constraints.
Authors: Sumanth Tangirala (Rutgers University); Aravind Sivaramakrishnan (Rutgers University); Ewerton Vieira (Rutgers University); Edgar Granados (Rutgers University); Konstantin Mischaikow (Rutgers University ); Kostas Bekris (Rutgers University)
Abstract: Estimating the region of attraction (RoA) for robot controllers is crucial for safe operation and integration. Many existing methods, limited by the need for closed-form expressions, do not suit data-driven controllers, while trajectory-based methods are overly data-intensive. We previously showed that Morse Graphs—directed acyclic graphs capturing non-linear dynamics—can efficiently estimate RoAs without an analytical model, though they falter with high-dimensional systems. This paper introduces Morse Graph-aided discovery of Regions of Attraction in a learned Latent Space (MORALS). Combining auto-encoding neural networks with Morse Graphs, MORALS efficiently predicts attractors and their RoAs for data-driven controllers in complex systems like a 67-dim humanoid robot and a 96-dim three-fingered manipulator. It projects the dynamics into a latent space and constructs Morse Graphs representing the bistability of the underlying dynamics to detect stable versus unstable behaviors. Evaluation shows data-efficient RoA estimation in high-dimensional robotic datasets.
Authors: Piotr Kicki (Poznan University of Technology); Davide Tateo (Technische Universität Darmstadt); Puze Liu (Technische Universität Darmstadt); Jonas Günster (TU Darmstadt); Jan Peters (TU Darmstadt); Krzysztof Walas (Poznan University of Technology)
Abstract: Trajectory planning under kinodynamic constraints is fundamental for advanced robotics applications that require safe, dexterous, reactive, and rapid skills in complex environments. This paper introduces a new approach to safe reinforcement learning by combining learning-to-plan methods with reinforcement learning, resulting in a novel integration of black-box learning of motion primitives and optimization. We show that the proposed method outperforms state-of-the-art in challenging scenarios such as planning to hit in robot air hockey.
Abstract: Event cameras are bio-inspired vision sensors with much lower latency and bandwidth than standard cameras. This talk will present current trends and opportunities with event cameras to increase safety and robustness of autonomous systems.