Game-Theoretic Planning for Risk-Aware Interactive Agents

Links: pdf, video, bibtex

Abtract

Modeling the stochastic behavior of interacting agents is key for safe motion planning. In this paper, we study the interaction of risk-aware agents in a game-theoretical framework. Under the entropic risk measure, we derive an iterative algorithm for approximating the intractable feedback Nash equilibria of a risk-sensitive dynamic game. We use an iteratively linearized approximation of the system dynamics and a quadratic approximation of the cost function in solving a backward recursion for finding feedback Nash equilibria. In this respect, the algorithm shares a similar structure with DDP and iLQR methods. We conduct experiments in a set of challenging scenarios such as roundabouts. Compared to ignoring the game interaction or the risk sensitivity, we show that our risk-sensitive game-theoretic framework leads to more time-efficient, intuitive, and safe behaviors when facing underlying risks and uncertainty.

Video

Bibtex

@inproceedings{wang2020game,
    title={Game-Theoretic Planning for Risk-Aware Interactive Agents},
    author={Mingyu Wang and Negar Mehr and Adrien Gaidon and Mac Schwager},
    booktitle={IROS},
    year={2020},
}