Probabilistic Symmetry for Multi-Agent Dynamics-猫眼课题宝

DOI：

发表时间：

2022-05

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Sophia Sun;R. Walters;Jinxi Li;Rose Yu

学习多智能体动力学是一个核心的人工智能问题，在机器人技术和自动驾驶领域有广泛应用。虽然大多数现有研究侧重于确定性预测，但生成概率预测以量化不确定性并评估风险对于运动规划和避碰等下游决策任务至关重要。多智能体动力学通常包含内部对称性。通过利用对称性，特别是旋转等变性，我们不仅可以提高预测准确性，还能改善不确定性校准。我们引入能量分数（Energy Score）这一合理评分规则来评估概率预测。我们提出一种新颖的深度动力学模型——概率等变连续卷积（Probabilistic Equivariant Continuous Convolution，PECCO），用于多智能体轨迹的概率预测。PECCO扩展了等变连续卷积，以对多个智能体的联合速度分布进行建模。它利用动力学积分将不确定性从速度传播到位置。在合成数据集和真实世界数据集上，与非等变基线相比，PECCO在准确性和校准方面都有显著提高。

Learning multi-agent dynamics is a core AI problem with broad applications in robotics and autonomous driving. While most existing works focus on deterministic prediction, producing probabilistic forecasts to quantify uncertainty and assess risks is critical for downstream decision-making tasks such as motion planning and collision avoidance. Multi-agent dynamics often contains internal symmetry. By leveraging symmetry, specifically rotation equivariance, we can improve not only the prediction accuracy but also uncertainty calibration. We introduce Energy Score, a proper scoring rule, to evaluate probabilistic predictions. We propose a novel deep dynamics model, Probabilistic Equivariant Continuous COnvolution (PECCO) for probabilistic prediction of multi-agent trajectories. PECCO extends equivariant continuous convolution to model the joint velocity distribution of multiple agents. It uses dynamics integration to propagate the uncertainty from velocity to position. On both synthetic and real-world datasets, PECCO shows significant improvements in accuracy and calibration compared to non-equivariant baselines.

Probabilistic Symmetry for Multi-Agent Dynamics

文献摘要

相似文献