50 Years of Robotics Symposium:

Robot Motion Planning: Achievements and Emerging Approaches

A Special Session at the IEEE/RSJ International Conference on Intelligent Robots and Systems

Ron Alterovitz
Department of Computer Science
University of North Carolina at Chapel Hill

Maxim Likhachev
Robotics Institute
Carnegie Mellon University

Date: Wednesday, September 28, 2011
Time: 8:00am - 9:30am
Location: Continental Ballroom 5, Hilton at Union Square, San Francisco


The last 50 years of robotics have seen tremendous advances in motion planning for mobile ground robots, aerial vehicles, medical robots, and personal robots, and in the domains of structural biology and computer animation. Yet, adoption of motion planning methods in robotic systems fielded in the real world has been limited.

In this symposium, we will explore and discuss key achievements in the area of motion planning as well as emerging approaches for planning robot motions in new real-world contexts. The symposium will feature a keynote talk by motion planning pioneer Prof. Tomas Lozano-Perez from MIT followed by a series of papers on new motion planning approaches.

We are excited to bring together members of the motion planning community to discuss accomplishments in the field and emerging approaches. We look forward to seeing you there.

Keynote Talk

Speaker: Prof. Tomas Lozano-Perez, MIT

Title: Motion Planning: Goals and Information

Abstract: The classic motion planning formulation involves reaching some goal (a robot configuration or set of configurations) in a known environment. However, if we are interested in a real robot task, such as cleaning a house, it involves thousands of motion planning goals performed in an environment with enormous uncertainty, arising from sources ranging from incomplete knowledge of which objects are relevant to sensing and control error. This talk addresses these two issues: (a) how does one derive motion planning goals from task specifications and (b) how does one plan in the presence of uncertainty.

Biography: Tomas Lozano-Perez is the School of Engineering Professor of Teaching Excellence at MIT, a member of the Department of Electrical Engineering and Computer Science and of the Computer Science (EECS) and Artificial Intelligence Laboratory (CSAIL). He has all his degrees (SB '73, SM '76, PhD '80) from MIT. He is a Fellow of the AAAI, the recipient of the NSF Presidential Young Investigator Award and the IEEE Robotics and Automation Society's Pioneer Award. Professor Lozano-Perez's current research focuses on approaches to robot planning and perception in the presence of uncertainty. He has also made contributions to robot motion planning (the configuration-space approach), computer vision (interpretation-tree approach to object recognition), to machine learning (multiple-instance learning), to medical imaging (automatic registration for frameless stereotaxy) and computational chemistry (drug activity prediction and protein structure determination from NMR & X-ray data).

Schedule of Presentations

  • 8:00am - 8:30am:
    Keynote presentation by Prof. Tomas Lozano-Perez, MIT.
  • 8:30am - 8:45am:
    Conflict-Free Route Planning in Dynamic Environments
    Adriaan W. ter Mors, Delft Univ. of Tech.
  • 8:45am - 8:50am:
    Kinodynamic Motion Planning with State Lattice Motion Primitives
    Mihail Pivtoraiko, Carnegie Mellon Univ., Alonzo Kelly, Carnegie Mellon Univ.
  • 8:50am - 8:55am:
    Efficient Motion Planning for Manipulation Robots in Environments with Deformable Objects
    Barbara Frank, Univ. of Freiburg, Cyrill Stachniss, Univ. of Freiburg, Nichola Abdo, Univ. of Freiburg, Wolfram Burgard, Univ. of Freiburg
  • 8:55am - 9:00am:
    Learning Dimensional Descent Planning for a Highly-Articulated Robot Arm
    Paul Vernaza, Univ. of Pennsylvania, Daniel D. Lee, Univ. of Pennsylvania
  • 9:00am - 09:15:
    A Simplified Model of RRT Coverage for Kinematic Systems
    Joel Esposito, US Naval Acad.
  • 9:15am - 9:30am:
    Space-Filling Trees: A New Perspective on Motion Planning Via Incremental Search
    James Kuffner, Carnegie Mellon Univ., Steven M LaValle, Univ. of Illinois