Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation

TL;DR

Intention-Net combines deep learning and path planning in a hierarchical system to enable delivery robots to navigate reliably in unfamiliar environments with minimal prior information.

Contribution

The paper introduces a novel two-level hierarchical navigation system integrating an end-to-end neural motion controller with a high-level path planner for goal-directed autonomous navigation.

Findings

The intention-net provides robust local navigation from monocular images.

Integration with a path planner improves generalization to new environments.

Preliminary results show effective navigation in unfamiliar office settings.

Abstract

How can a delivery robot navigate reliably to a destination in a new office building, with minimal prior information? To tackle this challenge, this paper introduces a two-level hierarchical approach, which integrates model-free deep learning and model-based path planning. At the low level, a neural-network motion controller, called the intention-net, is trained end-to-end to provide robust local navigation. The intention-net maps images from a single monocular camera and "intentions" directly to robot controls. At the high level, a path planner uses a crude map, e.g., a 2-D floor plan, to compute a path from the robot's current location to the goal. The planned path provides intentions to the intention-net. Preliminary experiments suggest that the learned motion controller is robust against perceptual uncertainty and by integrating with a path planner, it generalizes effectively to new environments and goals.