Active exploration for robust object detection

Authors:
Javier Velez;Garrett Hemann;Albert S. Huang;Ingmar Posner;Nicholas Roy
Affiliations:
MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA;MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA;MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA;Mobile Robotics Group, Dept. of Engineering Science, Oxford University, Oxford, UK;MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA
Venue:
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
Year:
2011

Citing 8
Cited 1

Near-optimal sensor placements in Gaussian processes

ICML '05 Proceedings of the 22nd international conference on Machine learning
Efficient Discriminant Viewpoint Selection for Active Bayesian Recognition

International Journal of Computer Vision
A General Method for Sensor Planning in Multi-Sensor Systems: Extension to Random Occlusion

International Journal of Computer Vision
A generative framework for fast urban labeling using spatial and temporal context

Autonomous Robots
Online planning algorithms for POMDPs

Journal of Artificial Intelligence Research
Navigating, Recognizing and Describing Urban Spaces With Vision and Lasers

International Journal of Robotics Research
The Belief Roadmap: Efficient Planning in Belief Space by Factoring the Covariance

International Journal of Robotics Research
Real-Time decision making for large POMDPs

AI'05 Proceedings of the 18th Canadian Society conference on Advances in Artificial Intelligence

Viewpoint based mobile robotic exploration aiding object search in indoor environment

Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Today, mobile robots are increasingly expected to operate in ever more complex and dynamic environments. In order to carry out many of the higher-level tasks envisioned a semantic understanding of a workspace is pivotal. Here our field has benefited significantly from successes in machine learning and vision: applications in robotics of off-the-shelf object detectors are plentiful. This paper outlines an online, any-time planning framework enabling the active exploration of such detections. Our approach exploits the ability to move to different vantage points and implicitly weighs the benefits of gaining more certainty about the existence of an object against the physical cost of the exploration required. The result is a robot which plans trajectories specifically to decrease the entropy of putative detections. Our system is demonstrated to significantly improve detection performance and trajectory length in simulated and real robot experiments.