The safety-critical nature of autonomous vehicle (AV) operation necessitates development of task-relevant algorithms that can reason about safety at the system level and not just at the component level. To reason about the impact of a perception failure on the entire system performance, such task-relevant algorithms must contend with various challenges: complexity of AV stacks, high uncertainty in the operating environments, and the need for real-time performance. To overcome these challenges, in this work, we introduce a Q-network called SPARQ (abbreviation for Safety evaluation for Perception And Recovery Q-network) that evaluates the safety of a plan generated by a planning algorithm, accounting for perception failures that the planning process may have over-looked. This Q-network can be queried during system runtime to assess whether a proposed plan is safe for execution or poses potential safety risks. If a violation is detected, the network can then recommend a corrective plan while accounting for the perceptual failure. We validate our algorithm using the NuPlan-Vegas dataset, demonstrating its ability to handle cases where a perception failure compromises a proposed plan while the corrective plan remains safe. We observe an overall accuracy and recall of 90% while sustaining a frequency of 42Hz on the unseen testing dataset. We compare our performance to a popular reachability - based baseline and analyze some interesting properties of our approach in improving the safety properties of an AV pipeline. Website: vatsuak.github.io/sparq

Hamilton-Jacobi (HJ) reachability analysis is a powerful framework for ensuring safety and performance in autonomous systems. However, existing methods typically rely on a white-box dynamics model of the system, limiting their applicability in many practical robotics scenarios where only a black-box model of the system is available. In this work, we propose a novel reachability method to compute reachable sets and safe controllers for black-box dynamical systems. Our approach efficiently approximates the Hamiltonian function using samples from the black-box dynamics. This Hamiltonian is then used to solve the HJ Partial Differential Equation (PDE), providing the reachable set of the system. The proposed method can be applied to general nonlinear systems and can be seamlessly integrated with existing reachability toolboxes for white-box systems to extend their use to black-box systems. Through simulation studies on a black-box slip-wheel car and a quadruped robot, we demonstrate the effectiveness of our approach in accurately obtaining the reachable sets for blackbox dynamical systems.

Behavior cloning (BC) is a widely used approach in imitation learning where a robot learns a control policy by observing an expert supervisor. However the learned policy can make errors and might lead to safety violations which limits their utility in safety-critical robotics applications. While prior works have tried improving a BC policy via additional real or synthetic action labels adversarial training or runtime filtering none of them explicitly focus on reducing the BC policy's safety violations during training time. We propose SAFE-GIL a design-time method to learn safety-aware behavior cloning policies. SAFE-GIL deliberately injects adversarial disturbance in the system during data collection to guide the expert towards safety-critical states. This disturbance injection simulates potential policy errors that the system might encounter during the test time. By ensuring that training more closely replicates expert behavior in safety-critical states our approach results in safer policies despite policy errors during the test time. We further develop a reachability-based method to compute this adversarial disturbance. We compare SAFE-GIL with various behavior cloning techniques and online safety-filtering methods in three domains autonomous ground navigation aircraft taxiing and aerial navigation on a quadrotor testbed. Our method demonstrates a significant reduction in safety failures particularly in low data regimes where the likelihood of learning errors and therefore safety violations is higher. See our website here: https://y-u-c.github.io/safegil/.

Hamilton-Jacobi (HJ) reachability analysis is a widely adopted verification tool to provide safety and performance guarantees for autonomous systems. However, it involves solving a partial differential equation (PDE) to compute a safety value function, whose computational and memory complexity scales exponentially with the state dimension, making its direct application to large-scale systems intractable. To overcome these challenges, DeepReach, a recently proposed learning-based approach, approximates high-dimensional reachable tubes using neural networks (NNs). While shown to be effective, the accuracy of the learned solution decreases with system complexity. One of the reasons for this degradation is a soft imposition of safety constraints during the learning process, which corresponds to the boundary conditions of the PDE, resulting in inaccurate value functions. In this work, we propose ExactBC, a variant of DeepReach that imposes safety constraints exactly during the learning process by restructuring the overall value function as a weighted sum of the boundary condition and the NN output. Moreover, the proposed variant no longer needs a boundary loss term during the training process, thus eliminating the need to balance different loss terms. We demonstrate the efficacy of the proposed approach in significantly improving the accuracy of the learned value function for four challenging reachability tasks: a rimless wheel system with state resets, collision avoidance in a cluttered environment, autonomous rocket landing, and multi-aircraft collision avoidance.

Modern legged robot morphologies assign most of their actuated degrees of freedom (DoF's) to the limbs and designs continue to converge to twelve DoF quadrupeds with three actuators per leg and a rigid torso often modeled as a Single Rigid Body (SRB). This is in contrast to the animal kingdom, which provides tantalizing hints that core actuation of a jointed torso confers substantial benefit for efficient agility. Unfortunately, the limited specific power of available actuators continues to hamper roboticists' efforts to capitalize on this bio-inspiration. This paper presents the initial steps in a comparative study of the costs and benefits associated with a traditionally neglected torso degree of freedom: a twisting spine. We use trajectory optimization to explore how a one-DoF, axially twisting spine might help or hinder a set of axially-active (twisting) behaviors: trots, sudden turns while bounding, and parkour-style wall jumps. By optimizing for minimum electrical energy or average power, intuitive cost functions for robots, we avoid hand-tuning the behaviors and explore the activation of the spine. Initial evidence suggests that for lower energy behaviors the spine increases the electrical energy required when compared to the rigid torso, but for higher energy runs the spine trends toward having no effect or reducing the electrical work. These results support future, more bio-inspired versions of the spine with inherent stiffness or dampening built into their mechanical design.