Reinforcement learning optimizes robot arm design to reduce joint load
Kinematic Reward, Measured Effort: Hardware-Validated RL Morphology Optimization of a Planar 2R Manipulator
Robotics
Summary
Designing robot arms to move efficiently can be tricky, especially when relying only on computer simulations. The authors use a type of artificial intelligence called reinforcement learning to improve the shape and size of a simple two-joint robot arm so it moves better along certain paths. They checked their design not only in simulation but also on a real robot arm, showing the AI-designed arm reduces the strain on its joints. This helps build robot arms that last longer and work more smoothly in real-world tasks.
What this means in practice
- •For robot designers: Optimize robotic arm designs to reduce joint stress for improved durability and efficiency in manufacturing tasks.
- •For industrial automation engineers: Implement AI-driven morphology optimization to customize robot arms for specific repetitive path tasks, lowering mechanical wear.
Authors
Gunesh Gupta, Arvind Kumar Mishra, Sohom Chakrabarty
Abstract
Yoshikawa's Manipulability Index is generally used as a classical measure to define an optimal morphology of a manipulator. However, any such optimization is almost always studied as a purely kinematic quantity in simulation and is rarely validated on hardware. We present a reinforcement-learning framework with RSL-RL PPO that optimizes the morphology of a 2R SCARA-type manipulator arm with Yoshikawa's kinematic manipulability index as a core reward, and the analytically derived closed-form optimum for the circular task is used to verify that our method recovers it. Then the same method is applied to custom elliptical and rectangular paths having no analytical optimum. The RL-optimized morphologies are then transferred to a 2R hardware manipulator to validate its effect in reduction of joint load in the hardware. Compared to the worst morphology, the optimum morphology delivered by our method reduces second joint load by 38.4 +/- 0.6% for the ellipse path and 41.3 +/- 0.3% for the rectangle, and first joint load by 15%.