Abstract
Imitation learning has shown great potential for enabling robots to acquire complex manipulation behaviors. However, these algorithms suffer from high sample complexity in long-horizon tasks, where compounding errors accumulate over the task horizons. We present PRIME ( PR imitive-based IM itation with data E fficiency), a behavior primitive-based framework designed for improving the data efficiency of imitation learning. PRIME scaffolds robot tasks by decomposing task demonstrations into primitive sequences, followed by learning a high-level control policy to sequence primitives through imitation learning. Our experiments demonstrate that PRIME achieves a significant performance improvement in multi-stage manipulation tasks, with 10–34% higher success rates in simulation over state-of-the-art baselines and 20–48% on physical hardware.
Funding Information
  • IIIS
  • Tsinghua University
  • Todor Stoyanov
  • Wallenberg AI, Autonomous Systems, and Software Program
  • National Science Foundation (EFRI-2318065, FRR-2145283)
  • Office of Naval Research (N00014-22-1-2204)
  • UT Good Systems
  • Machine Learning Laboratory