A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer

conference paper A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer accepted yes Patrick Thomas Mayer author 2448310009-0009-6800-1273 Jan Rexilius author 2457360000-0002-4579-214X 102 department 26th International Conference on Control, Automation and Systems (ICCAS) Institute for Building Intelligence project This paper presents a hybrid control architecture for dynamic robotic picking tasks. The framework combines a Deep Reinforcement Learning policy for high-level interception with a dedicated Inverse Kinematics controller for precise terminal grasping, while mitigating precision limitations of monolithic learning-based approaches. The framework utilizes a Proximal Policy Optimization agent to approach moving targets, seamlessly transitioning to an Inverse Kinematics solver that reduces terminal orientational and positional errors while minimizing cumulative control effort. To facilitate deployment on physical hardware, a robust sim-to-real pipeline incorporating system identification, domain randomization, and latency injection is employed. Experimental results on a physical Franka Emika Panda manipulator validate this hybrid architecture. The system achieves an 80% success rate in pick-and-place tasks, compared to 60.8% for unadapted baselines, with no safety-critical violations such as joint limit breaches or collisions observed during testing. 2026Sapporo eng Reinforcement LearningHybrid ControlSim-to-RealRobotic ManipulationInverse Kinematics. P.T. Mayer, J. Rexilius, in: n.d. Mayer, Patrick Thomas ; Rexilius, Jan: A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer. In: P. T. Mayer and J. Rexilius, “A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer,” presented at the 26th International Conference on Control, Automation and Systems (ICCAS), Sapporo. Mayer, Patrick Thomas, and Jan Rexilius. A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer. @inproceedings{Mayer_Rexilius, title={A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer}, author={Mayer, Patrick Thomas and Rexilius, Jan} } Mayer PT, Rexilius J. A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer. Mayer, Patrick Thomas, and Jan Rexilius. “A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer,” n.d. Mayer, P. T., & Rexilius, J. (n.d.). A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer. Presented at the 26th International Conference on Control, Automation and Systems (ICCAS), Sapporo. 71742026-09-21T16:30:06Z2026-09-21T19:31:37Z