Adaptive Conformal Prediction for Motion Planning among Dynamic Agents
Adaptive Conformal Prediction for Motion Planning among Dynamic Agents
复制标题
DOI：
10.48550/arxiv.2212.00278
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Anushri Dixit;Lars Lindemann;Skylar X. Wei;Matthew Cleaveland;George Pappas;J. Burdick
中科院分区：
文献类型：
--
作者：
Anushri Dixit;Lars Lindemann;Skylar X. Wei;Matthew Cleaveland;George Pappas;J. Burdick
提出了一种基于自适应保角预测的动态智能体间运动规划算法。我们考虑一个确定性控制系统，并使用轨迹预测器来预测动态智能体的未来运动，假设其服从一个未知的分布。然后，我们利用来自自适应共形预测的想法来动态量化在线数据流中的预测不确定性。具体地说，我们提供了一种在线算法，使用延迟的代理观测来获得具有概率覆盖的多步提前预测的不确定性集。这些不确定性集在模型预测控制器中使用，以在动态代理之间安全导航。虽然大多数现有的数据驱动预测都是启发式地量化预测不确定性，但我们以一种无分布的、自适应的方式量化真正的预测不确定性，甚至允许捕捉预测质量和代理运动的变化。我们在一个模拟案例研究中对我们的算法进行了经验评估，其中无人机避开了飞行的飞盘。
This paper proposes an algorithm for motion planning among dynamic agents using adaptive conformal prediction. We consider a deterministic control system and use trajectory predictors to predict the dynamic agents' future motion, which is assumed to follow an unknown distribution. We then leverage ideas from adaptive conformal prediction to dynamically quantify prediction uncertainty from an online data stream. Particularly, we provide an online algorithm uses delayed agent observations to obtain uncertainty sets for multistep-ahead predictions with probabilistic coverage. These uncertainty sets are used within a model predictive controller to safely navigate among dynamic agents. While most existing data-driven prediction approached quantify prediction uncertainty heuristically, we quantify the true prediction uncertainty in a distribution-free, adaptive manner that even allows to capture changes in prediction quality and the agents' motion. We empirically evaluate of our algorithm on a simulation case studies where a drone avoids a flying frisbee.