用障碍物引导的强化算法，让挂车倒车更安全高效。
GPU-Accelerated Barrier-Rate Guided MPPI Control for Tractor-Trailer Systems
- 将障碍物约束融入路径积分更新，引导搜索更安全轨迹
- 单块GPU实现100Hz以上控制频率，8个障碍物场景下停车间隙更优
- 适合智能驾驶中复杂泊车任务，尤其有行人干扰的环境
如挂车、场内运输车等铰接车辆常需在有行人的密集区域倒车和操控。本文提出障碍物速率引导的模型预测路径积分（BR-MPPI）控制方法，将控制屏障函数（CBF）约束直接嵌入路径积分更新过程。该方法通过引导重要性采样分布趋向无碰撞、动态可行的轨迹，增强MPPI的探索能力并提升轨迹鲁棒性。在高保真CarMaker仿真器中对一辆12米长的挂车进行评估，任务为停车场内的倒车与前向泊车。实验表明，单块GPU上BR-MPPI在含八个障碍物的场景下可实现超过100 Hz的控制输入计算频率，并在停车间隙表现上优于标准MPPI基线及带碰撞代价的MPPI基线。
原文摘要 · Abstract (English)
Articulated vehicles such as tractor-trailers, yard trucks, and similar platforms must often reverse and maneuver in cluttered spaces where pedestrians are present. We present how Barrier-Rate guided Model Predictive Path Integral (BR-MPPI) control can solve navigation in such challenging environments. BR-MPPI embeds Control Barrier Function (CBF) constraints directly into the path-integral update. By steering the importance-sampling distribution toward collision-free, dynamically feasible trajectories, BR-MPPI enhances the exploration strength of MPPI and improves robustness of resulting trajectories. The method is evaluated in the high-fidelity CarMaker simulator on a 12 [m] tractor-trailer tasked with reverse and forward parking in a parking lot. BR-MPPI computes control inputs in above 100 [Hz] on a single GPU (for scenarios with eight obstacles) and maintains better parking clearance than a standard MPPI baseline and an MPPI with collision cost baseline.
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。