让自动驾驶赛车在多车竞速中预测对手意图并安全超车
M-Predictive Spliner: Enabling Spatiotemporal Multi-Opponent Overtaking for Autonomous Racing
- 用卡尔曼滤波追踪多对手并关联轨迹
- 通过高斯过程回归预测对手位置与速度，实现91.65%超车成功率
- 适合高速自主赛车系统开发，提升复杂场景决策能力
无限制的多智能体竞速是机器人决策的前沿挑战，要求在极限性能下做出判断。以往方法或忽略时空信息，或仅支持单对手场景。本文提出M-Predictive Spliner方法，采用基于卡尔曼滤波的多对手追踪器，实现对手跨观测关联（ReID）；同时对所有已观测对手轨迹进行空间与速度的高斯过程回归（GPR），提供未来行为预测以计算超车动作。该方法在1:10比例的物理自动驾驶赛车上验证，超车成功率达91.65%，在相同速度下相较现有最优方法安全性平均提升10.13个百分点，展现出高性能自主竞速的潜力。
原文摘要 · Abstract (English)
Unrestricted multi-agent racing presents a significant research challenge, requiring decision-making at the limits of a robot's operational capabilities. While previous approaches have either ignored spatiotemporal information in the decision-making process or been restricted to single-opponent scenarios, this work enables arbitrary multi-opponent head-to-head racing while considering the opponents' future intent. The proposed method employs a KF-based multi-opponent tracker to effectively perform opponent ReID by associating them across observations. Simultaneously, spatial and velocity GPR is performed on all observed opponent trajectories, providing predictive information to compute the overtaking maneuvers. This approach has been experimentally validated on a physical 1:10 scale autonomous racing car, achieving an overtaking success rate of up to 91.65% and demonstrating an average 10.13%-point improvement in safety at the same speed as the previous SotA. These results highlight its potential for high-performance autonomous racing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。