From motor control to embodied intelligence - Google DeepMind

deepmind.google · 1,100 words · saved by 1 readers

Using human and animal motions to teach robots to dribble a ball, and simulated humanoid characters to carry boxes and play football Humanoid character learning to traverse an obstacle course through trial-and-error, which can lead to idiosyncratic solutions. Heess, et al. "Emergence of locomotion behaviours in rich environments" (2017). Five years ago, we took on the challenge of teaching a fully articulated humanoid character to traverse obstacle courses. This demonstrated what reinforcement learning (RL) can achieve through trial-and-error but also highlighted two challenges in solving embodied intelligence: Here, we describe a solution to both challenges called neural probabilistic motor primitives (NPMP), involving guided learning with movement patterns derived from humans and animals, and discuss how this approach is used in our Humanoid Football paper, published today in Science Robotics. We also discuss how this same approach enables humanoid full-body manipulation from vision,

August 31, 2022 Research Siqi Liu, Leonard Hasenclever, Steven Bohez, Guy Lever, Zhe Wang, S. M. Ali Eslami, Nicolas Heess Using human and animal motions to teach robots to dribble a ball, and simulated humanoid characters to carry boxes and play football Humanoid character learning to traverse an obstacle course through trial-and-error, which can lead to idiosyncratic solutions. Heess, et al. "Emergence of locomotion behaviours in rich environments" (2017). Five years ago, we took on the challenge of teaching a fully articulated humanoid character to traverse obstacle courses. This…

From motor control to embodied intelligence - Google DeepMind

related reading