Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots

University of California, Berkeley


Deep reinforcement learning algorithms require large and diverse datasets in order to learn successful policies for perception-based mobile navigation. However, gathering such datasets with a single robot can be prohibitively expensive. Collecting data with multiple different robotic platforms with possibly different dynamics is a more scalable approach to large-scale data collection. But how can deep reinforcement learning algorithms leverage such heterogeneous datasets? In this work, we propose a deep reinforcement learning algorithm with hierarchically integrated models (HInt). At training time, HInt learns separate perception and dynamics models, and at test time, HInt integrates the two models in a hierarchical manner and plans actions with the integrated model. This method of planning with hierarchically integrated models allows the algorithm to train on datasets gathered by a variety of different platforms, while respecting the physical capabilities of the deployment robot at test time. Our real world navigation experiments show that HInt outperforms conventional hierarchical policies and single-source approaches.


At training time, HInt separately trains a perception model and a dynamics model, while at test time, HInt combines the perception and dynamics model into a single model for integrated planning and execution. Our modular training procedure enables HInt to train the perception model using data gathered by multiple platforms, such as ground robots and even people recording video with a hand-held camera, while our integrated model attest time ensures the perception model only considers trajectories which are dynamically feasible.


Implementation Details