Robust Policy Search for an Agile Ground Vehicle Under Perception Uncertainty
Robust Policy Search for an Agile Ground Vehicle Under Perception Uncertainty
复制标题
DOI：
10.1109/iros51168.2021.9636552
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
S. Sefati;Subhransu Mishra;Matthew Sheckells;Kapil D. Katyal;Jin Bai;Gregory Hager;Marin Kobilarov
中科院分区：
文献类型：
--
作者：
S. Sefati;Subhransu Mishra;Matthew Sheckells;Kapil D. Katyal;Jin Bai;Gregory Hager;Marin Kobilarov
为在存在不确定性的情况下运行的机器人系统学习稳健的策略是一项具有挑战性的任务。为了安全导航，除了环境和车辆动力学的自然随机性之外，在运动规划期间必须考虑与动态实体（例如，行人）相关联的感知不确定性。为此，我们构建了一个算法，内置的不确定性的鲁棒性，直接最小化的置信上限的预期成本的轨迹，而不是采用一个标准的方法的基础上最小化的预期成本本身。感知不确定性被纳入到政策搜索框架预测每个行人的意图信念和传播他们的状态分布的时间使用闭环目标导向的动态。我们在仿真中训练了该策略，并表明它可以转移到敏捷的地面车辆上，以便在存在感知不确定性的行人的情况下成功地进行自主机器人导航。我们进一步表明，该政策的上级性能的政策，不考虑行人的意图和感知的不确定性。
Learning robust policies for robotic systems operating in presence of uncertainty is a challenging task. For safe navigation, in addition to the natural stochasticity of the environment and vehicle dynamics, the perception uncertainty associated with dynamic entities, e.g. pedestrians, must be accounted for during motion planning. To this end, we construct an algorithm with built-in robustness to uncertainty by directly minimizing an upper confidence bound on the expected cost of trajectories instead of employing a standard approach based on minimizing the expected cost itself. Perception uncertainty is incorporated into the policy search framework by predicting each pedestrian’s intent belief and propagating their state distribution in time using closed-loop goal-directed dynamics. We train the policy in simulation and show that it could be transferred to an agile ground vehicle for successful autonomous robot navigation in presence of pedestrians with perception uncertainty. We further show the superior performance of this policy over a policy that does not consider pedestrian intent and perception uncertainty.