Towards General Purpose Robots at Scale: Lifelong Learning and Learning to Use Memory
This work aims to advance general-purpose robotics for deployment in everyday settings like homes, though it appears incremental as it builds on existing benchmarks and methods.
The thesis tackles the challenge of enabling robots to operate autonomously over long time horizons in unstructured environments by addressing memory and lifelong learning, proposing t-DGR for state-of-the-art performance on Continual World benchmarks and a framework using human demonstrations to improve success rates on Memory Gym tasks.
The widespread success of artificial intelligence in fields like natural language processing and computer vision has not yet fully transferred to robotics, where progress is hindered by the lack of large-scale training data and the complexity of real-world tasks. To address this, many robot learning researchers are pushing to get robots deployed at scale in everyday unstructured environments like our homes to initiate a data flywheel. While current robot learning systems are effective for certain short-horizon tasks, they are not designed to autonomously operate over long time horizons in unstructured environments. This thesis focuses on addressing two key challenges for robots operating over long time horizons: memory and lifelong learning. We propose two novel methods to advance these capabilities. First, we introduce t-DGR, a trajectory-based deep generative replay method that achieves state-of-the-art performance on Continual World benchmarks, advancing lifelong learning. Second, we develop a framework that leverages human demonstrations to teach agents effective memory utilization, improving learning efficiency and success rates on Memory Gym tasks. Finally, we discuss future directions for achieving the lifelong learning and memory capabilities necessary for robots to function at scale in real-world settings.