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

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.

Published in 1st Annual Conference on Robot Learning (CoRL 2017)

References in corpus (4)

• End to End Learning for Self-Driving Cars
• From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots
• Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
• DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

Cited by in corpus (20)

• Variational End-to-End Navigation and Localization
• Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans
• Spatial Action Maps for Mobile Manipulation
• Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI
• Combining Optimal Control and Learning for Visual Navigation in Novel Environments
• APPLE: Adaptive Planner Parameter Learning from Evaluative Feedback
• Reactive Reinforcement Learning in Asynchronous Environments
• Fully Convolutional Search Heuristic Learning for Rapid Path Planners
• Towards navigation without precise localization: Weakly supervised learning of goal-directed navigation cost map
• Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning
• A review of motion planning algorithms for intelligent robotics
• A Lifelong Learning Approach to Mobile Robot Navigation
• Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps
• DeepMPCVS: Deep Model Predictive Control for Visual Servoing
• REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter
• DeepGoal: Learning to Drive with driving intention from Human Control Demonstration
• APPLR: Adaptive Planner Parameter Learning from Reinforcement
• Subgoal Search For Complex Reasoning Tasks
• Toward Agile Maneuvers in Highly Constrained Spaces: Learning from Hallucination
• Visual Perspective Taking for Opponent Behavior Modeling