发表机构
University of Bologna; University of Twente（博洛尼亚大学; 特文特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出Real2Sim2Real流水线，结合轨迹匹配等方法校准7自由度Franka Emika Panda机器人动力学，训练TQC智能体，实现力矩控制机器人Sim2Real迁移，提升了跟踪精度与鲁棒性。
AI 中文摘要
将强化学习策略从仿真迁移到真实机器人仍是一项重大挑战，尤其在处理低级别力矩控制时，微小的建模误差都可能导致不稳定或不安全的行为。本研究提出一种Real2Sim2Real流水线，结合轨迹匹配、遗传算法参数优化与域随机化，以改进力矩控制机械臂的Sim2Real迁移。使用7自由度Franka Emika Panda机器人，首先通过最小化真实与仿真关节轨迹间的误差，识别摩擦、惯性及重力补偿参数；随后利用这些校准后的动力学模型，在仿真环境中训练基于TQC的强化学习智能体。将训练好的策略在Gazebo与MuJoCo环境中评估，最终部署到真实机器人上。结果表明，参数调优后跟踪精度与策略鲁棒性显著提升，在多个目标到达任务中实现了从仿真到真实机器人的平滑策略迁移，本研究凸显了精确物理建模对实现稳定且可泛化的基于力矩的强化学习策略的有效性。
英文摘要
Transferring reinforcement learning policies from simulation to Real-World robots remains a major challenge, particularly when dealing with low-level torque control, where even small modelling inaccuracies can lead to unstable or unsafe behaviours. In this work, we propose a Real2Sim2Real pipeline that improves Sim2Real transfer for torque-controlled robotic arms by combining trajectory matching, parameter optimization via genetic algorithms, and domain randomization. Using the 7-DOF Franka Emika Panda robot, we first identify friction, inertia, and gravity compensation parameters by minimizing the error between real and simulated joint trajectories. These calibrated dynamics are then used to train a TQC-based reinforcement learning agent in simulation. The trained policy is evaluated in both Gazebo and MuJoCo environments, and finally deployed on the real robot. Our results demonstrate a significant improvement in tracking accuracy and policy robustness after parameter tuning, with smooth policy transfer from simulation to the Real-World across multiple target-reaching tasks. This work highlights the effectiveness of accurate physical modelling in enabling stable and generalizable torque-based reinforcement learning policies.
Comments6 pages, 8 figures. Presented at the 2026 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM 2026)
