SCORP: Scene-Consistent Multi-agent Diffusion Planning with Stable Online Reinforcement Post-Training for Cooperative Driving
SCORP:具有稳定在线强化学习后训练的场景一致多智能体扩散规划用于协作驾驶
机构 * School of Information Science and Technology, Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)信息科学与技术学院) ; Middle East Technology University (METU)(中东技术大学) ; Robotics and Autonomous Systems Thrust, Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)机器人与自主系统方向) ; School of Computer Science and Technology, Qinghai University(青海大学计算机科学与技术学院)
专题命中 扩散模型 :diffusion(title,abstract)
AI总结 SCORP通过场景条件多智能体去噪架构和两层马尔可夫决策过程提升多智能体协作驾驶的场景一致性和效率,实验表明其在安全性和效率指标上优于现有基线方法。