A high-precision object pose estimation and fine manipulation method based on visual-tactile fusion
By defining master and slave objects and combining particle filtering technology and tactile information, the posture changes of slave objects are estimated in real time, which solves the problem of low accuracy of visual posture estimation in dynamic environments and achieves high-precision object posture estimation and fine operation.
Patent Information
- Application Number
- CN202411637620.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-15
- Publication Date
- 2025-09-26
- Estimated Expiration
- 2044-11-15
AI Technical Summary
Existing vision-based object pose estimation methods have low accuracy in dynamic environments, and traditional vision-tactile fusion methods fail to effectively deal with pose changes caused by object sliding or movement.
By defining a master object and a slave object, the posture changes of the master object are tracked in real time. Particle filtering technology is combined with tactile information to estimate the posture changes of the slave object relative to the robot's end effector, including translational and rotational slippage. Tactile sensors are used to detect sliding signals, and collision simulation and particle filtering algorithms are combined to perform accurate posture estimation.
It achieves high-precision pose estimation in dynamic environments, with a translation error of 1-2 mm and a rotation error of approximately 2 degrees. It is suitable for a variety of dynamic operation scenarios and improves the robot's ability to respond in dynamic interactive environments.