Non Normalized Shared-Constraint Dynamic Games for Human-Robot Collaboration with Asymmetric Responsibility

TL;DR

This paper introduces a novel dynamic game framework for human-robot collaboration that allows asymmetric responsibility in safety constraints, enabling more flexible and realistic cooperation in shared workspaces.

Contribution

It presents a non-normalized equilibrium concept for shared safety constraints and integrates it into a receding-horizon control scheme for human-robot navigation.

Findings

Effective modeling of asymmetric safety responsibility.

Successful implementation in a receding-horizon control scheme.

Enhanced cooperation in shared workspace navigation.

Abstract

This paper proposes a dynamic game formulation for cooperative human-robot navigation in shared workspaces with obstacles, where the human and robot jointly satisfy shared safety constraints while pursuing a common task. A key contribution is the introduction of a non-normalized equilibrium structure for the shared constraints. This structure allows the two agents to contribute different levels of effort towards enforcing safety requirements such as collision avoidance and inter-players spacing. We embed this non-normalized equilibrium into a receding-horizon optimal control scheme.