Cooperative Robot Motion Planning for Human Contact Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional robots struggle to efficiently cooperate with human workers in dynamic environments, particularly in high-mix low-volume production and mass customization, due to their inability to adapt to unexpected human actions and frequent changes in work content, leading to inefficiencies and potential interruptions.
Innovation Solution
A cooperative robotic system that includes a goal planning module to generate multiple task end states, a load estimation module to detect and respond to applied forces, and a motion planning module to dynamically adjust robot movements based on load status and human interaction, ensuring seamless collaboration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the robot executes pre-planned actions without re-planning, then the robot maintains continuous operation, but the robot cannot respond to unexpected human actions which interrupts cooperative work
Solution Approach 1:
The robot transitions from static pre-planned motion to dynamic motion planning that continuously adapts to human actions. The motion planning module generates new motion plans in real-time based on detected human actions, allowing the robot to dynamically adjust its behavior while maintaining continuous operation.
Solution Approach 2:
The system implements feedback by detecting human actions during robot operation and using this information to generate updated motion plans. The action detection module continuously monitors human actions and feeds this information back to the motion planning module, creating a closed-loop control system that responds to unexpected events.
2Adaptability or versatility
If the robot re-plans motion upon detecting human contact, then the robot responds to human actions, but the re-planning process interrupts work and reduces efficiency
Solution Approach 1:
The system performs preliminary actions by pre-planning multiple motion plans in advance. When human contact is detected, the robot selects from pre-computed alternative motion plans rather than performing complete re-planning, thus responding to human actions while minimizing work interruptions.
Solution Approach 2:
Instead of complete re-planning upon detecting human actions, the system performs partial re-planning by selecting from pre-computed motion plans or making minor adjustments to the current plan. This partial action approach provides sufficient response to human contact while avoiding the productivity loss of full re-planning cycles.
3Reliability
If the robot requires specific force patterns from human workers after contact, then the robot can continue operation, but the human worker must perform non-intuitive operations that reduce efficiency
Solution Approach 1:
The robot serves itself by autonomously detecting human actions and generating appropriate motion plans without requiring the human worker to perform specific force patterns. The system eliminates the need for humans to apply predetermined force patterns, making operation more intuitive while maintaining continuous operation.
4Productivity
If the robot moves to memorized positions repeatedly, then the robot can perform tasks efficiently, but the robot cannot adapt to changing work content and object positions in cooperative work
Solution Approach 1:
The robot transitions from static memorized position execution to dynamic motion planning that adapts to changing work content. The motion planning module generates motion plans based on real-time detection of object positions and human actions, allowing the robot to maintain efficiency while adapting to dynamic cooperative work environments.
Solution Approach 2:
The system uses feedback from object detection and human action detection to continuously update motion plans. Rather than repeatedly moving to pre-memorized positions, the robot detects current object positions and human actions, then generates appropriate motion plans, enabling adaptation to changing work content while maintaining efficient task execution.
Data Source
AI summary
In example implementations described herein, there are systems and methods for controlling a cooperative robotic device including generating, for the cooperative robotic device, a plurality of candidate task end states associated with a first task. The method may further include selecting, for the cooperative robotic device, a first task end state from the plurality of candidate task end states, receiving load data regarding a load experienced by the cooperative robotic device, and selecting, based on the load data, a second task end state from the plurality of candidate task end states.