Towards Risk‐Free Trustworthy Artificial Intelligence: Significance and Requirements
Given the tremendous potential and influence of artificial intelligence (AI) and algorithmic
decision‐making (DM), these systems have found wide‐ranging applications across diverse …
decision‐making (DM), these systems have found wide‐ranging applications across diverse …
Provably safe deep reinforcement learning for robotic manipulation in human environments
Deep reinforcement learning (RL) has shown promising results in the motion planning of
manipulators. However, no method guarantees the safety of highly dynamic obstacles, such …
manipulators. However, no method guarantees the safety of highly dynamic obstacles, such …
Increasing perceived safety in motion planning for human-drone interaction
Safety is crucial for autonomous drones to operate close to humans. Besides avoiding
unwanted or harmful contact, people should also perceive the drone as safe. Existing safe …
unwanted or harmful contact, people should also perceive the drone as safe. Existing safe …
Safe reinforcement learning of dynamic high-dimensional robotic tasks: navigation, manipulation, interaction
Safety is a fundamental property for the real-world deployment of robotic platforms. Any
control policy should avoid dangerous actions that could harm the environment, humans, or …
control policy should avoid dangerous actions that could harm the environment, humans, or …
Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications
Integrating learning-based techniques, especially reinforcement learning, into robotics is
promising for solving complex problems in unstructured environments. However, most …
promising for solving complex problems in unstructured environments. However, most …
Fully-automated verification of linear systems using reachability analysis with support functions
While reachability analysis is one of the major techniques for formal verification of dynamical
systems, the requirement to adequately tune algorithm parameters often prevents its …
systems, the requirement to adequately tune algorithm parameters often prevents its …
Unleashing mixed-reality capability in Deep Reinforcement Learning-based robot motion generation towards safe human–robot collaboration
The integration of human–robot collaboration yields substantial benefits, particularly in terms
of enhancing flexibility and efficiency within a range of mass-personalized manufacturing …
of enhancing flexibility and efficiency within a range of mass-personalized manufacturing …
RAIL: Reachability-Aided Imitation Learning for Safe Policy Execution
Imitation learning (IL) has shown great success in learning complex robot manipulation
tasks. However, there remains a need for practical safety methods to justify widespread …
tasks. However, there remains a need for practical safety methods to justify widespread …
VRoboCoop-Trajectory Planning to Achieve Reliable and Trustworthy Human-Robot Collaboration
The collaboration between humans and robots offers opportunities that are not achievable
separately. However, a strategy for collaboration is required, as they differ in their behavior …
separately. However, a strategy for collaboration is required, as they differ in their behavior …
Data-Driven Closed-Loop Reachability Analysis for Nonlinear Human-in-the-Loop Systems Using Gaussian Mixture Model
This article presents data-driven algorithms to perform the reachability analysis of nonlinear
human-in-the-loop (HITL) systems. Such systems require consideration of the human control …
human-in-the-loop (HITL) systems. Such systems require consideration of the human control …