Humanoid Robot Trajectory Recovery After Collision Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot programming systems fail to effectively handle collision avoidance in humanoid robots, often resulting in abrupt stops or mechanical changes in direction, which do not provide a satisfactory user experience and are computationally intensive to calculate safety areas around obstacles.
Innovation Solution
A method for controlling the trajectory of humanoid robots that involves calculating a single safety area around the robot, using on-board sensors to detect obstacles, and adjusting the robot's trajectory and speed to avoid collisions while maintaining a smooth, human-like movement by rejoining the initial target point, incorporating data fusion and sensor data from laser lines, imaging, acoustic, and contact detectors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If safety areas are calculated for all obstacles using prior art methods, then collision avoidance capability is improved, but computational intensity increases significantly
Solution Approach 1:
The patent applies local quality by calculating safety areas selectively only for obstacles that are both detectable by sensors and potentially collidable based on robot trajectory, rather than uniformly for all obstacles. This localized approach reduces computational intensity while maintaining collision avoidance capability for relevant obstacles.
Solution Approach 2:
The patent implements partial action by computing safety areas for only a subset of obstacles that meet specific criteria (detectable and potentially collidable), rather than performing complete safety area calculations for all obstacles in the environment. This partial computation significantly reduces processing requirements.
2Reliability
If the robot executes abrupt stops or mechanical changes in direction to avoid collision, then collision avoidance is achieved, but user experience deteriorates due to unnatural mechanical behavior
Solution Approach 1:
The patent applies dynamics by continuously adjusting robot trajectory and speed in response to detected obstacles, rather than executing fixed abrupt stops. The control system dynamically modifies motion parameters to achieve smooth, natural-looking avoidance maneuvers that maintain user experience while ensuring collision avoidance.
Solution Approach 2:
The patent implements feedback by using sensor data to continuously monitor obstacle positions and robot trajectory, then adjusting motion commands in real-time. This closed-loop control enables smooth, adaptive trajectory modifications that appear natural rather than mechanical, improving user experience while maintaining safety.
3Reliability
If the robot changes trajectory to avoid collision, then collision avoidance is achieved, but the ability to rejoin the original trajectory is lost
Solution Approach 1:
The patent applies preliminary action by planning trajectory adjustments that consider future rejoining of the original path. The control system proactively modifies trajectory in advance to account for obstacle avoidance while maintaining the ability to return to the target point, ensuring both collision avoidance and task completion efficiency.
Solution Approach 2:
The patent implements feedback by continuously monitoring both obstacle positions and original trajectory parameters, enabling the robot to dynamically adjust its avoidance path and timing. This real-time feedback allows the robot to rejoin the original trajectory at appropriate moments, maintaining productivity while ensuring safety.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a humanoid robot which can move on its lower limb to execute a trajectory. According to the invention, the robot is capable of detecting intrusion of obstacles in a safety zone defined around its body as a function of its speed. Preferably when the robot executes a predefined trajectory, for instance a part of a choreography, the robot which avoids collision with an obstacle will rejoin its original trajectory after avoidance of the obstacle. Rejoining trajectory and speed of the robot are adapted so that it is resynchronized with the initial trajectory. Advantageously, the speed of the joints of the upper members of the robot is adapted in case the distance with an obstacle decreases below a preset minimum. Also, the joints are stopped in case a collision of the upper members with the obstacle is predicted.