Learning navigational maps by observing human motion patterns
- 1 May 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10504729,p. 4333-4340
Abstract
Observing human motion patterns is informative for social robots that share the environment with people. This paper presents a methodology to allow a robot to navigate in a complex environment by observing pedestrian positional traces. A continuous probabilistic function is determined using Gaussian process learning and used to infer the direction a robot should take in different parts of the environment. The approach learns and filters noise in the data producing a smooth underlying function that yields more natural movements. Our method combines prior conventional planning strategies with most probable trajectories followed by people in a principled statistical manner, and adapts itself online as more observations become available. The use of learning methods are automatic and require minimal tuning as compared to potential fields or spline function regression. This approach is demonstrated testing in cluttered office and open forum environments using laser and vision sensing modalities. It yields paths that are similar to the expected human behaviour without any a priori knowledge of the environment or explicit programming.Keywords
This publication has 16 references indexed in Scilit:
- Imitation Learning of Positional and Force Skills Demonstrated via Kinesthetic Teaching and Haptic InputAdvanced Robotics, 2011
- Robot motor skill coordination with EM-based Reinforcement Learning2010
- Modeling and decision making in spatio-temporal processes for environmental surveillance2010
- A survey of robot learning from demonstrationRobotics and Autonomous Systems, 2009
- Sensor Registration for Robotic Applications2008
- Randomized Kinodynamic Motion Planning with Moving ObstaclesThe International Journal of Robotics Research, 2002
- Experiences with an interactive museum tour-guide robotArtificial Intelligence, 1999
- Human Motion Analysis: A ReviewComputer Vision and Image Understanding, 1999
- Interpolation of Spatial Data1999
- Pfinder: real-time tracking of the human bodyIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997