LUCIDGames: Online Unscented Inverse Dynamic Games for Adaptive Trajectory Prediction and Planning
LUCIDGames: Online Unscented Inverse Dynamic Games for Adaptive Trajectory Prediction and Planning
复制标题
DOI：
10.1109/lra.2021.3074880
复制
发表时间：
2020-11
影响因子：
5.2
通讯作者：
Simon Le Cleac’h;M. Schwager;Zachary Manchester
中科院分区：
文献类型：
--
作者：
Simon Le Cleac’h;M. Schwager;Zachary Manchester
现有的博弈论规划方法假设机器人知道其他代理的目标函数先验，而在实际情况下，这是很少的情况。这封信介绍LUCIDGames，逆最优控制算法，能够估计其他代理的目标函数在真实的时间，并将这些估计在线到一个滚动时域博弈论规划。LUCIDGames通过在递归参数估计框架中重铸逆最优控制问题来解决该问题。LUCIDGames使用无迹卡尔曼滤波器（UKF）来迭代更新其他代理的成本函数参数的贝叶斯估计，随着从其他代理的观察轨迹收集更多数据，在线改进该估计。然后，规划者考虑到其他代理的贝叶斯参数估计的不确定性，规划的轨迹机器人受到不确定性椭圆约束。该算法假设机器人和环境中的其他代理之间没有显式的通信或协调。LUCIDGames的MPC实现演示了复杂自动驾驶场景的实时性能，更新频率为40 Hz。实验结果表明，LUCIDGames提高了机器人的性能，现有的博弈论和传统的MPC规划方法。我们的LUCIDGames的实现可以在https://github.com/RoboticExplorationLab/LUCIDGames.jl上找到。
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 letter 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.