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

by   Wei Gao, et al.
Panasonic Corporation of North America
National University of Singapore

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.


page 2

page 6

page 7

page 8


Integrating Algorithmic Planning and Deep Learning for Partially Observable Navigation

We propose to take a novel approach to robot system design where each bu...

ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints

Robotic navigation has been approached as a problem of 3D reconstruction...

Planning Beyond the Sensing Horizon Using a Learned Context

Last-mile delivery systems commonly propose the use of autonomous roboti...

Multiple Waypoint Navigation in Unknown Indoor Environments

Indoor motion planning focuses on solving the problem of navigating an a...

Deep Local Trajectory Replanning and Control for Robot Navigation

We present a navigation system that combines ideas from hierarchical pla...

QMDP-Net: Deep Learning for Planning under Partial Observability

This paper introduces the QMDP-net, a neural network architecture for pl...

Unifying Map and Landmark Based Representations for Visual Navigation

This works presents a formulation for visual navigation that unifies map...

Please sign up or login with your details

Forgot password? Click here to reset