LUCIDGames: Online Unscented Inverse Dynamic Games for Adaptive Trajectory Prediction and Planning
This addresses adaptive trajectory prediction and planning for autonomous systems like driving, where prior knowledge of other agents' goals is often unavailable, representing a novel method for a known bottleneck rather than a foundational advance.
The paper tackles the problem of robots not knowing other agents' objective functions in game-theoretic planning by introducing LUCIDGames, an algorithm that estimates these functions in real time using an unscented Kalman filter and integrates them into a planner, achieving real-time performance at 40 Hz and improving robot performance over existing methods.
Existing game-theoretic planning methods assume that the robot knows the objective functions of the other agents a priori while, in practical scenarios, this is rarely the case. This paper introduces LUCIDGames, an inverse optimal control algorithm that is able to estimate the other agents' objective functions in real time, and incorporate those estimates online into a receding-horizon game-theoretic planner. LUCIDGames solves the inverse optimal control problem by recasting it in a recursive parameter-estimation framework. LUCIDGames uses an unscented Kalman filter (UKF) to iteratively update a Bayesian estimate of the other agents' cost function parameters, improving that estimate online as more data is gathered from the other agents' observed trajectories. The planner then takes account of the uncertainty in the Bayesian parameter estimates of other agents by planning a trajectory for the robot subject to uncertainty ellipse constraints. The algorithm assumes no explicit communication or coordination between the robot and the other agents in the environment. An MPC implementation of LUCIDGames demonstrates real-time performance on complex autonomous driving scenarios with an update frequency of 40 Hz. Empirical results demonstrate that LUCIDGames improves the robot's performance over existing game-theoretic and traditional MPC planning approaches. Our implementation of LUCIDGames is available at https://github.com/RoboticExplorationLab/LUCIDGames.jl.