The safety filter: A unified view of safety-critical control in autonomous systems

KC Hsu, H Hu, JF Fisac - Annual Review of Control, Robotics …, 2023 - annualreviews.org
Recent years have seen significant progress in the realm of robot autonomy, accompanied
by the expanding reach of robotic technologies. However, the emergence of new …

Online update of safety assurances using confidence-based predictions

K Nakamura, S Bansal - 2023 IEEE International Conference …, 2023 - ieeexplore.ieee.org
Robots such as autonomous vehicles and assistive manipulators are increasingly operating
in dynamic environ-ments and close physical proximity to people. In such scenarios, the …

Learning-aware safety for interactive autonomy

H Hu, Z Zhang, K Nakamura, A Bajcsy… - arXiv preprint arXiv …, 2023 - arxiv.org
One of the outstanding challenges for the widespread deployment of robotic systems like
autonomous vehicles is ensuring safe interaction with humans without sacrificing efficiency …

Deception game: Closing the safety-learning loop in interactive robot autonomy

H Hu, Z Zhang, K Nakamura, A Bajcsy… - 7th Annual Conference …, 2023 - openreview.net
An outstanding challenge for the widespread deployment of robotic systems like
autonomous vehicles is ensuring safe interaction with humans without sacrificing …

Updating Robot Safety Representations Online from Natural Language Feedback

L Santos, Z Li, L Peters, S Bansal, A Bajcsy - arXiv preprint arXiv …, 2024 - arxiv.org
Robots must operate safely when deployed in novel and human-centered environments, like
homes. Current safe control approaches typically assume that the safety constraints are …

Refining Obstacle Perception Safety Zones via Maneuver-Based Decomposition

S Topan, Y Chen, E Schmerling… - 2023 IEEE Intelligent …, 2023 - ieeexplore.ieee.org
A critical task for developing safe autonomous driving stacks is to determine whether an
obstacle is safety-critical, ie, poses an imminent threat to the autonomous vehicle. Our …

Learning Approximated Maximal Safe Sets via Hypernetworks for MPC-Based Local Motion Planning

B Derajić, MK Bouzidi, S Bernhard, W Hönig - arXiv preprint arXiv …, 2024 - arxiv.org
This paper presents a novel learning-based approach for online estimation of maximal safe
sets for local motion planning tasks in mobile robotics. We leverage the idea of …

Decision boundary learning for safe vision-based navigation via Hamilton-Jacobi reachability analysis and support vector machine

T Toufighi, M Bui, R Shrestha… - 6th Annual Learning for …, 2024 - proceedings.mlr.press
We develop a self-supervised learning method that can predict safe and unsafe high-level
waypoints for robot navigation in the form of a decision boundary given solely a RGB image …

Gait Switching and Enhanced Stabilization of Walking Robots with Deep Learning-based Reachability: A Case Study on Two-link Walker

X Xia, JJ Choi, A Agrawal, K Sreenath… - arXiv preprint arXiv …, 2024 - arxiv.org
Learning-based approaches have recently shown notable success in legged locomotion.
However, these approaches often lack accountability, necessitating empirical tests to …

Parameterized Fast and Safe Tracking (FaSTrack) using Deepreach

HJ Jeong, Z Gong, S Bansal, S Herbert - arXiv preprint arXiv:2404.07431, 2024 - arxiv.org
Fast and Safe Tracking (FaSTrack) is a modular framework that provides safety guarantees
while planning and executing trajectories in real time via value functions of Hamilton-Jacobi …