Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport

TL;DR

This paper introduces Long-HOT, a new environment and a modular hierarchical framework for long-horizon object transport, enabling efficient exploration and navigation in complex scenes, with significant performance improvements over existing methods.

Contribution

The paper presents a novel Long-HOT environment and a hierarchical transport policy that combines exploration and motion planning, advancing long-horizon embodied navigation capabilities.

Findings

Our method outperforms baselines on Long-HOT and MultiOn benchmarks.

The hierarchical approach generalizes well to more complex scenes.

Modular design enhances exploration and long-horizon planning.

Abstract

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.