Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport
This addresses challenges in long-horizon navigation and exploration for robotics and AI systems, representing an incremental advancement in modular methods for complex tasks.
The paper tackles the problem of long-horizon object transport in embodied AI by proposing a new task and a modular hierarchical framework, achieving significant performance improvements over baselines and demonstrating generalization to harder scenes with training on simpler ones.
We address key challenges in long-horizon embodied exploration and navigation by proposing a new object transport task and a novel modular framework for temporally extended navigation. Our first contribution is the design of a novel Long-HOT environment focused on deep exploration and long-horizon planning where the agent is required to efficiently find and pick up target objects to be carried and dropped at a goal location, with load constraints and optional access to a container if it finds one. Further, we propose a modular hierarchical transport policy (HTP) that builds a topological graph of the scene to perform exploration with the help of weighted frontiers. Our hierarchical approach uses a combination of motion planning algorithms to reach point goals within explored locations and object navigation policies for moving towards semantic targets at unknown locations. Experiments on both our proposed Habitat transport task and on MultiOn benchmarks show that our method significantly outperforms baselines and prior works. Further, we validate the effectiveness of our modular approach for long-horizon transport by demonstrating meaningful generalization to much harder transport scenes with training only on simpler versions of the task.