Alborz Aghamaleki Sarvestani

Milad Shafiee Ashtiani, Alborz Aghamaleki Sarvestani, Alexander Badri-Spröwitz

Animals locomote robustly and agile, albeit significant sensorimotor delays of their nervous system. The sensorimotor control of legged robots is implemented with much higher frequencies-often in the kilohertz range-and sensor and actuator delays in the low millisecond range. But especially at harsh impacts with unknown touch-down timing, legged robots show unstable controller behaviors, while animals are seemingly not impacted. Here we examine this discrepancy and suggest a hybrid robotic leg and controller design. We implemented a physical, parallel joint compliance dimensioned in combination with an active, virtual leg length controller. We present an extensive set of systematic experiments both in computer simulation and hardware. Our hybrid leg and controller design shows previously unseen robustness, in the presence of sensorimotor delays up to 60 ms, or control frequencies as low as 20 Hz, for a drop landing task from 1.3 leg lengths high and with a passive compliance ratio of 0.7. In computer simulations, we report successful drop-landings of the hybrid compliant leg from 3.8 leg lengths (1.2 m) for a 2 kg quadruped robot with 100 Hz control frequency and a sensorimotor delay of 35 ms. The results of our presented hybrid leg design and control provide a further explanation for the performance robustness of animals, and the resulting discrepancy between animals and legged robots.

Steve Heim, Felix Ruppert, Alborz A. Sarvestani et al.

Learning instead of designing robot controllers can greatly reduce engineering effort required, while also emphasizing robustness. Despite considerable progress in simulation, applying learning directly in hardware is still challenging, in part due to the necessity to explore potentially unstable parameters. We explore the concept of shaping the reward landscape with training wheels: temporary modifications of the physical hardware that facilitate learning. We demonstrate the concept with a robot leg mounted on a boom learning to hop fast. This proof of concept embodies typical challenges such as instability and contact, while being simple enough to empirically map out and visualize the reward landscape. Based on our results we propose three criteria for designing effective training wheels for learning in robotics. A video synopsis can be found at https://youtu.be/6iH5E3LrYh8.