IEEE Robotics and Automation Letters 2023

Members of the ELLIS Unit Delft, Cognitive Robotics (Autonomous Multi-Robots Lab; Javier Alonso Mora), contributed their work “Learning to Play Trajectory Games Against Opponents with Unknown Objectives” to the IEEE Robotics and Automation Letters. This work will also be presented at IROS 2023.

Many autonomous agents, such as intelligent vehicles, are inherently required to interact with one another. Game theory provides a natural mathematical tool for robot motion planning in such interactive settings. However, tractable algorithms for such problems usually rely on a strong assumption, namely that the objectives of all players in the scene are known. To make such tools applicable for ego-centric planning with only local information, we propose an adaptive model-predictive game solver, which jointly infers other players' objectives online and computes a corresponding generalized Nash equilibrium (GNE) strategy. The adaptivity of our approach is enabled by a differentiable trajectory game solver whose gradient signal is used for maximum likelihood estimation (MLE) of opponents' objectives. This differentiability of our pipeline facilitates direct integration with other differentiable elements, such as neural networks (NNs). Furthermore, in contrast to existing solvers for cost inference in games, our method handles not only partial state observations but also general inequality constraints. In two simulated traffic scenarios, we find superior performance of our approach over both existing game-theoretic methods and non-game-theoretic model-predictive control (MPC) approaches. We also demonstrate the real-time planning capabilities and robustness of our approach in a hardware experiment.

Liu Xinjie, Lasse Peters, and Javier Alonso-Mora. "Learning to Play Trajectory Games Against Opponents with Unknown Objectives." IEEE Robotics and Automation Letters (2023).