Towards Multi-Morphology Controllers with Diversity and Knowledge Distillation

arXiv:2404.14625v1 Announce Type: cross
Abstract: Finding controllers that perform well across multiple morphologies is an important milestone for large-scale robotics, in line with recent advances via foundation models in other areas of machine learning. However, the challenges of learning a single controller to control multiple morphologies make the `one robot one task' paradigm dominant in the field. To alleviate these challenges, we present a pipeline that: (1) leverages Quality Diversity algorithms like MAP-Elites to create a dataset of many single-task/single-morphology …

abstract advances arxiv challenges control cs.lg cs.ne cs.ro distillation diversity foundation however knowledge line machine machine learning multiple robot robotics scale type via