Home research People General Info Seminars Resources Intranet
| Algorithms & Applcations Group | Home | Research | Publications | People | Resources | News
Algorithms & Applications Group
User-Guided Motion Planning

Overview

Motion planning is a difficult and widely studied problem in robotics. However, humans perform motions with relative ease. User-guided planners concern themselves with attempting to harness intuition from a human operator to improve planning efficiency or quality. The example below shows a human operator influencing a PRM planning to significantly improve performance over a fully automatic method.

Comparison between user-guided versus non-user-guided planning

Why collaborate with a user?

  • Sampling-based planners have difficulty finding narrow passages
  • How can a user help?
    • Given and environment, a user or oracle could help identify narrow passages
    • Given a roadmap, a user or oracle could help identify disconnected components
    • Identifying these areas for the planner limits the search space for a solution, thus making the problem easier to solve

Overview

Region Steering is a collaborative planner in which the user specifies workspace regions to guide a PRM planner. Region Steering uses an interactive communication model.

  • User
    • The user interacts with the planner through a virtual representation of the environment.
    • The user can create, remove, and modify regions both prior to and during execution.
    • The user can specify attract regions to encourage sampling, or avoid regions to prevent it.
  • Planner
    • The planner follows the user's guidance and displays its progress.
    • The planner displays the current roadmap at all times.
    • The planner focuses on generating more samples within attract regions.
    • The planner discards samples that encroach on avoid regions.
    • To preserve completeness, the entire environment is considered an attract region.

Communication Framework

Example

Input Features

The user input occurs in the workspace, which offers a lot of flexibility for input devices.

  • No relationship between the robot and the input device is required.
  • Many-DOF robots can be steered with simple devices like mice.
  • Any device that can map to a plane or volume can be used, allowing Region Steering to support many alternatives such as haptics or 3D mice.

Demo

Vizmo++ Overview

Vizmo++ is a tool for visualizing and interacting with motion planning problems. It offers:

  • Visualization of environments, robots, and roadmaps.
  • Tools for editing and authoring.
  • A framework for executing collaborative planners.

Visualization

Vizmo++ allows users to examine environments and roadmaps.

Editing

Vizmo++ allows users to edit environments and roadmaps.

Collaborative Planning

Vizmo++ offers a framework for running collaborative planners like Region Steering.

On the Theory of User-guided Planning, Jory Denny, Jonathan Colbert, Qin Hongsen, Nancy M. Amato, In Proc. IEEE Int. Conf. Intel. Rob. Syst. (IROS), pp. to appear, Daejeon, Korea, Oct 2016.
Proceedings(ps, pdf, abstract)

Collaborative Motion Planning, Jory Denny, Ph.D. Thesis, Department of Computer Science and Engineering, Texas A&M University, Aug 2016.
Ph.D. Thesis(ps, pdf, abstract)

A General Region-Based Framework for Collaborative Planning, Jory Denny, Read Sandstrom, Nancy M. Amato, In Proc. Inter. Symp. on Robotics Research (ISRR), pp. 563-579, Genova, Italy, Sep 2015.
Proceedings(ps, pdf, abstract)

A Region-Based Strategy for Collaborative Roadmap Construction, Jory Denny, Read Sandstrom, Nicole Julian, Nancy M. Amato, In Proc. Int. Wkshp. on Alg. Found. of Rob. (WAFR), pp. to appear, Istanbul, Turkey, Aug 2014.
Proceedings(ps, pdf, abstract)

VIZMO++: a Visualization, Authoring, and Educational Tool for Motion Planning, Aimée Vargas E., Jyh-Ming Lien, Nancy M. Amato, In Proc. IEEE Int. Conf. Robot. Autom. (ICRA), pp. 727-732, Orlando, Florida, To appear, May 2006. Also, Technical Report, TR05-014, Parasol Laboratory, Department of Computer Science, Texas A&M University, Sep 2005.
Proceedings(ps, pdf, abstract) Technical Report(ps, pdf, abstract)

Visualization Tools for Moving Objects, Aimée Vargas E., Masters Thesis, Parasol Laboratory, Department of Computer Science, Texas A&M University, Dec 2005.
Masters Thesis(ps, pdf, abstract)

Enhancing Randomized Motion Planners: Exploring with Haptic Hints, O. Burchan Bayazit, Guang Song, Nancy M. Amato, Autonomous Robots, 10(2):163-174, 2001. Also, In Proc. IEEE Int. Conf. Robot. Autom. (ICRA), pp. 529-536, Apr 2000. Also, Technical Report, TR99-021, Parasol Laboratory, Department of Computer Science, Texas A&M University, Oct 1999.
Proceedings(pdf, abstract)

Ligand Binding with OBPRM and Haptic User Input, O. Burchan Bayazit, Guang Song, Nancy M. Amato, In Proc. IEEE Int. Conf. Robot. Autom. (ICRA), pp. 954-959, May 2001.
Proceedings(ps, pdf, abstract)

Interactive Dynamic Simulation using Haptic Interaction, Wookho Son, Kyunghwan Kim, Nancy M. Amato, Jeffrey C. Trinkle, In Proc. IEEE Int. Conf. Intel. Rob. Syst. (IROS), pp. 145-150, Nov 2000.
Proceedings(ps, pdf, abstract)

Ligand Binding with OBPRM and Haptic User Input: Enhancing Automatic Motion Planning with Virtual Touch, O. Burchan Bayazit, Guang Song, Nancy M. Amato, Technical Report, TR00-025, Department of Computer Science and Engineering, Texas A&M University, Oct 2000.
Technical Report(ps, pdf, abstract)

An Interactive Generalized Motion Simulator (GMS) in an Object-Oriented Framework, Wookho Son, Kyunghwan Kim, Nancy M. Amato, In Proc. of Computer Animation (CA), pp. 176-181, May 2000.
Proceedings(ps, pdf, abstract)

Providing Haptic 'Hints' to Automatic Motion Planners, O. Burchan Bayazit, Guang Song, Nancy M. Amato, In Phantom Users Group Work. (PUG), Oct 1999.
Proceedings(ps, pdf, abstract)

Providing Haptic 'Hints' to Automatic Motion Planners, Nancy M. Amato, O. Burchan Bayazit, Kyunghwan Kim, Wookho Son, Guang Song, Technical Report, TR98-026, Department of Computer Science and Engineering, Texas A&M University, Nov 1998.


Supported by NSF

Project Alumni:O. Burchan Bayazit,Nicole Julian,Jyh-Ming Lien,Guang Song,Brennen Taylor,Aimée Vargas


Parasol Home | Research | People | General info | Seminars | Resources  

Parasol Laboratory, 425 Harvey R. Bright Bldg, 3112 TAMU, College Station, TX 77843-3112 
parasol-admin@cse.tamu.edu      Phone 979.458.0722     Fax 979.458.0718 

Department of Computer Science and Engineering | Dwight Look College of Engineering Dwight Look College of Engineering | Texas A&M University
    
Privacy statement: Computer Science and Engineering Engineering TAMU
Web Accessibility Policy and Law - Web Accessibility and Usability Standards  -   Contact Webmaster