Abstract –┬áConsider the task of a mobile robot autonomously navigating through an environment while detecting and mapping objects of interest using a noisy object detector. The robot must reach its destination in a timely manner, but is rewarded for correctly detecting recognizable objects to be added to the map, and penalized for false alarms. However, detector performance typically varies with vantage point, so the robot benefits from planning trajectories which maximize the efficacy of the recognition system.

This work describes an online, any-time planning framework enabling the active exploration of possible detections provided by an off-the-shelf object detector. We present a prob- abilistic approach where vantage points are identified which provide a more informative view of a potential object. The agent then weighs the benefit of increasing its confidence against the cost of taking a detour to reach each identified vantage point. The system is demonstrated to significantly improve detection and trajectory length in both simulated and real robot experiments.


Conceptual illustrations of: (a) robot following original trajectory towards the goal, in the presence of some object; (b) perception field for an object detector centred around the object hypothesis; (c) alternative path (dashed line) that follows a more alternative route. Lighter cell colours indicate a lower conditional entropy and therefore desirable vantage points for object recognition.

  • [PDF] J. Velez, G. Hemann, A. S. Huang, I. Posner, and N. Roy, “Planning to Perceive: Exploiting Mobility For Robust Object Detection,” in International Conference on Automated Planning and Scheduling, Freiburg, Germany, 2011.
    author = {Javier Velez and Garrett Hemann and Albert S. Huang and Ingmar Posner and Nicholas Roy},
    title = {Planning to Perceive: Exploiting Mobility For Robust Object Detection},
    booktitle = {International Conference on Automated Planning and Scheduling},
    year = {2011},
    address = {Freiburg, Germany},
    month = {June},
    award = {Best Student Paper},
    awardlink = {http://icaps11.icaps-conference.org/technical/papers.html#beststudentpaper},
    pdf = {http://www.robots.ox.ac.uk/~mobile/Papers/2011IJCAI_posner2.pdf},
    keywords = {Urban Classification, conference_posner},