Corpus ID: 19421773

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

  title={Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation},
  author={W. Gao and D. Hsu and Wee Sun Lee and Shengmei Shen and K. Subramanian},
  • W. Gao, D. Hsu, +2 authors K. Subramanian
  • Published 2017
  • Computer Science
  • ArXiv
  • How can a delivery robot navigate reliably to a destination in a new office building, with minimal prior information. [...] Key Method 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…Expand Abstract
    47 Citations
    Deep Local Trajectory Replanning and Control for Robot Navigation
    • 17
    • Highly Influenced
    • PDF
    Combining Optimal Control and Learning for Visual Navigation in Novel Environments
    • 49
    • PDF
    Spatial Action Maps for Mobile Manipulation
    • 8
    • Highly Influenced
    • PDF
    Variational End-to-End Navigation and Localization
    • 42
    • PDF
    Visual Navigation Among Humans with Optimal Control as a Supervisor
    • PDF
    Towards navigation without precise localization: Weakly supervised learning of goal-directed navigation cost map
    • 3
    • PDF
    Learning Navigation Behaviors End-to-End With AutoRL
    • 57
    • PDF
    DeepGoal: Learning to Drive with driving intention from Human Control Demonstration
    • 1
    • PDF


    From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots
    • 169
    • PDF
    Target-driven visual navigation in indoor scenes using deep reinforcement learning
    • 729
    • PDF
    Path Planning for Autonomous Vehicles in Unknown Semi-structured Environments
    • 397
    • PDF
    Real-Time Randomized Path Planning for Robot Navigation
    • 272
    End-to-End Training of Deep Visuomotor Policies
    • 1,944
    • PDF
    (CAD)$^2$RL: Real Single-Image Flight without a Single Real Image
    • 404
    • PDF
    Learning to Navigate in Complex Environments
    • 503
    • PDF
    End to End Learning for Self-Driving Cars
    • 1,978
    • Highly Influential
    • PDF
    DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
    • 975
    • PDF
    Planning algorithms
    • 5,464
    • PDF