Safety Guarantee

Safety guarantees in AI and robotics aim to ensure systems operate reliably and avoid harmful actions, a critical concern for deploying autonomous systems in real-world settings. Current research focuses on developing and verifying safety mechanisms using diverse approaches, including control barrier functions, reinforcement learning with constraints, and formal verification techniques like reachability analysis, often incorporating neural networks or Gaussian processes for modeling and prediction. These advancements are crucial for building trust and enabling wider adoption of AI-powered systems in safety-critical applications such as healthcare, autonomous driving, and robotics.

Papers

October 2, 2023

Simulation Assessment Guidelines towards Independent Safety Assurance of Autonomous Vehicles
Jim Cherian, Martin Slavik, Andrea Piazzoni, Roshan Vijay, Mohamed Azhar, Niels de Boer
Autonomous Vehicle Safety Guarantee Public Transit State Aware Guideline

September 15, 2023

Wasserstein Distributionally Robust Control Barrier Function using Conditional Value-at-Risk with Differentiable Convex Programming
Alaa Eddine Chriat, Chuangchuang Sun
Control Barrier Function Safety Constraint Safety Guarantee Distributionally Robust Value at Risk Differentiable Convex

September 7, 2023

A computationally lightweight safe learning algorithm
Dominik Baumann, Krzysztof Kowalczyk, Koen Tiels, Paweł Wachel
Gaussian Process Safety Guarantee Safe Learning Nadaraya Watson

September 3, 2023

Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy
Haimin Hu, Zixu Zhang, Kensuke Nakamura, Andrea Bajcsy, Jaime F. Fisac
Autonomous Vehicle Learning Dynamic Safety Guarantee Robot Autonomy Adversarial Reinforcement Learning Strategic Deception Safety Learning

July 1, 2023

Fast, Smooth, and Safe: Implicit Control Barrier Functions through Reach-Avoid Differential Dynamic Programming
Athindran Ramesh Kumar, Kai-Chieh Hsu, Peter J. Ramadge, Jaime F. Fisac
Safety Guarantee Safety Filter Differential Dynamic Programming Receding Horizon

June 30, 2023

Bayesian Optimization with Formal Safety Guarantees via Online Conformal Prediction
Yunchuan Zhang, Sangwoo Park, Osvaldo Simeone
Bayesian Optimization Safety Constraint Optimization Process Zeroth Order Safety Guarantee Online Conformal Prediction

June 8, 2023

Time-Optimal Path Tracking with ISO Safety Guarantees
Shohei Fujii, Quang-Cuong Pham
Human Robot Collaboration Robot Motion Safety Guarantee Safe Robot Path Tracking Time Optimal Control Robot Collision

April 17, 2023

Deep Continuum Deformation Coordination and Optimization with Safety Guarantees
Harshvardhan Uppaluru, Hossein Rastgoftar
Optimization Purpose Collision Avoidance Safety Guarantee Multi Agent Coordination Agent Team Continuum Deformation

March 29, 2023

Physical Deep Reinforcement Learning Towards Safety Guarantee
Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo
Deep Reinforcement Learning Safety Guarantee Reward Signal Critical Autonomous System

March 20, 2023

Chance-Constrained Multi-Robot Motion Planning under Gaussian Uncertainties
Anne Theurkauf, Justin Kottinger, Nisar Ahmed, Morteza Lahijanian
Multi Robot Safety Guarantee Kinodynamic Motion Robot Collision

March 8, 2023

Safe Machine-Learning-supported Model Predictive Force and Motion Control in Robotics
Janine Matschek, Johanna Bethge, Rolf Findeisen
Robotics Domain Safety Guarantee Force Control Motion Control Force Estimation Predictive Controller Stochastic MPC

March 3, 2023

Towards Safety Assured End-to-End Vision-Based Control for Autonomous Racing
Dvij Kalaria, Qin Lin, John M. Dolan
Reinforcement Learning End to End External Control Autonomous Racing Safety Guarantee Safety Critical Control Autonomous Pipeline

February 21, 2023

Probabilistic Risk Assessment for Chance-Constrained Collision Avoidance in Uncertain Dynamic Environments
Khaled A. Mustafa, Oscar de Groot, Xinwei Wang, Jens Kober, Javier Alonso-Mora
Safety Guarantee Risk Assessment Uncertain Dynamic Probabilistic Planning Based Collision Collision Probability Uncertain Dynamic Environment

January 26, 2023

A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks
David Boetius, Stefan Leue, Tobias Sutter
Neural Network Safety Guarantee Constrained Learning DNN Repair Early Termination Counterexample Guided Repair Robust Optimisation

December 12, 2022

Safe Reinforcement Learning with Probabilistic Guarantees Satisfying Temporal Logic Specifications in Continuous Action Spaces
Hanna Krasowski, Prithvi Akella, Aaron D. Ames, Matthias Althoff
Action Space Safe Reinforcement Learning Safety Guarantee Probabilistic Safety Vanilla Reinforcement Learning Probabilistic Temporal Logic

December 6, 2022

ISAACS: Iterative Soft Adversarial Actor-Critic for Safety
Kai-Chieh Hsu, Duy Phuong Nguyen, Jaime Fernández Fisac
Human SAFETY Safety Guarantee Actor Critic Reinforcement Learning Safety Learning

October 19, 2022

October 14, 2022

Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate
Dongjie Yu, Wenjun Zou, Yujie Yang, Haitong Ma, Shengbo Eben Li, Jingliang Duan, Jianyu Chen
Safe Reinforcement Learning Safety Guarantee Model Based Safe Reinforcement Learning

October 3, 2022

Probabilistic Safeguard for Reinforcement Learning Using Safety Index Guided Gaussian Process Models
Weiye Zhao, Tairan He, Changliu Liu
Reinforcement Learning Black Box Model Safety Guarantee Model Learning Safe Controller Forward Invariance

Safety Guarantee

Papers

Simulation Assessment Guidelines towards Independent Safety Assurance of Autonomous Vehicles

Wasserstein Distributionally Robust Control Barrier Function using Conditional Value-at-Risk with Differentiable Convex Programming

A computationally lightweight safe learning algorithm

Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy

Fast, Smooth, and Safe: Implicit Control Barrier Functions through Reach-Avoid Differential Dynamic Programming

Bayesian Optimization with Formal Safety Guarantees via Online Conformal Prediction

Time-Optimal Path Tracking with ISO Safety Guarantees

Deep Continuum Deformation Coordination and Optimization with Safety Guarantees

Physical Deep Reinforcement Learning Towards Safety Guarantee

Chance-Constrained Multi-Robot Motion Planning under Gaussian Uncertainties

Safe Machine-Learning-supported Model Predictive Force and Motion Control in Robotics

Towards Safety Assured End-to-End Vision-Based Control for Autonomous Racing

Probabilistic Risk Assessment for Chance-Constrained Collision Avoidance in Uncertain Dynamic Environments

A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks

Safe Reinforcement Learning with Probabilistic Guarantees Satisfying Temporal Logic Specifications in Continuous Action Spaces

ISAACS: Iterative Soft Adversarial Actor-Critic for Safety

Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes

Safe Planning in Dynamic Environments using Conformal Prediction

Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate

Probabilistic Safeguard for Reinforcement Learning Using Safety Index Guided Gaussian Process Models