Shared-Control Mobile Robot Teleoperation for Intent Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing teleoperation systems for mobile robots lack the ability to predict critical motion intended by human operators in domain-specific tasks, such as pick and place, due to the absence of haptic feedback, leading to increased cognitive load and inefficiencies.
Innovation Solution
A system and method for mobile robot teleoperation using shared control, which involves acquiring human operator input, reconstructing kinematic states, and using model predictive control to follow the human operator's trajectory and intended goal, minimizing cognitive load through autonomous assistance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If haptic feedback is provided to the human operator in teleoperation systems, then system stability is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts and removes the haptic feedback component from the teleoperation system. By eliminating the force sensing hardware and haptic feedback mechanisms, the system achieves the same operational stability through alternative means - specifically through visual feedback and autonomous robot capabilities, thereby resolving the contradiction between stability and complexity
Solution Approach 2:
The robot is empowered with autonomous capabilities to perform collision avoidance and determine operator intent independently. This self-service approach allows the robot to maintain system stability without requiring external haptic feedback from the operator, thus improving reliability while reducing hardware complexity
2Reliability
If haptic feedback is provided to the human operator, then system stability is improved, but loss of time occurs due to additional training requirements
Solution Approach 1:
By removing the haptic feedback system entirely, the patent eliminates the need for operators to learn how to interpret and respond to force feedback signals. This extraction of the haptic component directly reduces training time while maintaining stability through visual feedback and autonomous robot behavior
Solution Approach 2:
The patent substitutes the mechanical haptic feedback system with an information-based control approach using visual feedback and computational algorithms. This replacement eliminates the need for physical interaction training while maintaining system stability through software-based solutions
3Device complexity
If teleoperation with only visual feedback is used, then device complexity is reduced, but reliability decreases due to increased cognitive load on the operator
Solution Approach 1:
The robot performs autonomous collision avoidance and intent determination, serving itself by handling complex decision-making tasks. This reduces the cognitive load on the operator while maintaining high reliability, as the robot independently manages challenging aspects of the teleoperation task
Solution Approach 2:
The autonomous capabilities of the robot perform preliminary actions such as collision avoidance and path planning before the operator needs to intervene. This preliminary processing of complex tasks reduces operator cognitive load while maintaining system reliability through layered autonomy
4Productivity
If autonomous capabilities are added to the robot, then productivity is improved, but device complexity increases
Solution Approach 1:
The robot implements partial autonomy, performing only specific functions such as collision avoidance and intent determination independently. This selective application of autonomous capabilities improves productivity for critical sub-tasks without requiring full-system complexity, achieving efficiency gains with moderate control system complexity
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This disclosure relates to system and method to reconstruct human motion for mobile robot teleoperation using shared control. The method of the present disclosure acquire an input feed of a human operator to perform a task with assistance in a remote environment using shared control. The mobile robot reconstructs to follow a trajectory of the human operator towards the intended goal in the remote environment. The mobile robot determines at least one goal intended by the human operator based on a previously occurred state, a current kinematic state and a future trajectory of the human operator and a known position of the plurality of goals. The model predictive control generates at least one instruction to control the movement of the mobile robot to perform at least one of following the trajectory of the human operator and reaching the operator intended goal based on a joint angle position and a velocity.