This chapter presents two common perception interfaces for capturing the relevant motions during the demonstrations, including optical tracking systems and vision cameras. The optical tracking system employs a set of infrared optical markers for capturing the demonstrated motions. Based on the markers’ locations with respect to a fixed reference frame, poses of predefined rigid bodies are inferred over a set of discrete time instants. A Firefly MV CMOS camera from Point Grey has also been used for the observation of demonstrations. The task perception with vision cameras is performed via acquiring visual information from the environment in the form of sequences of images. While the optical tracking systems provide accurate and reliable means for capturing demonstrated tasks, the vision cameras allow natural and unrestrained motions during the demonstrations which can quickly be performed without the need for attaching markers on the objects in the scene.
Task Perception
2017-03-10
5 pages
Article/Chapter (Book)
Electronic Resource
English
Perception and decision in pedestrian task
TIBKAT | 1974
|Is Driving an Automatic Task? Dual-Task Performance and Hazard Perception
British Library Conference Proceedings | 1994
|MtpNet: Multi-Task Panoptic Driving Perception Network
IEEE | 2025
|Integrated Sensory-Motor Systems and Task Specific Perception
British Library Conference Proceedings | 1994
|Task-adaptable, pervasive perception for robots performing everyday manipulation
TIBKAT | 2020
|