Controlling robot torque and velocity based on context

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Robots are unable to assemble meals in food-service settings due to their inability to operate with appropriate torques in close proximity to humans and in environments where ingredients are unpredictably arranged, leading to potential injuries and damage to food textures and taste profiles.

Innovation Solution

The development of context-specific torque control for robots, which determines the necessary torque based on the task, environment, and proximity to obstacles, allowing for safe operation by limiting torque according to context-specific conditions such as free space, active contact, and collision likelihood, using models, neural networks, and simulations to adjust velocity, acceleration, and position limits.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Power

If the robot applies high torque to perform tasks such as scooping ice cream, then the task execution capability is improved, but the safety of human operators in proximity is compromised

Engineering Contradiction:
ImprovetorqueVSAvoidinjury risk to human
Core Design Contradiction:
PowerVSObject-affected harmful factors

Solution Approach 1:

The patent implements dynamic torque adjustment by continuously monitoring context parameters (human proximity, task type, environmental conditions) and adjusting the robot's torque output in real-time. This allows the robot to apply high torque only when necessary for task execution while automatically reducing torque when humans are in proximity, thus resolving the contradiction between task capability and safety.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system employs feedback mechanisms through sensors that detect human presence, robot position, and task requirements. This feedback loop enables the control system to continuously adjust torque levels based on current operational context, ensuring high torque is applied only when safe and appropriate for the task at hand.

Inventive Principle:
Principle #23Feedback

2Adaptability or versatility

If the robot operates in close proximity to humans, then the workspace flexibility is improved, but the torque limitation reduces task execution capability

Engineering Contradiction:
Improveworkspace flexibilityVSAvoidtorque
Core Design Contradiction:
Adaptability or versatilityVSPower

Solution Approach 1:

The patent enables dynamic torque adjustment based on spatial context, allowing the robot to operate with high torque in safe zones while automatically reducing torque when approaching human-proximity zones. This dynamic adaptation maintains workspace flexibility while ensuring safety constraints are met in different spatial contexts.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system applies different torque characteristics to different spatial zones within the workspace. High torque is permitted in areas distant from humans, while low torque is enforced in human-proximity zones. This local differentiation allows the robot to maintain both workspace flexibility and human safety simultaneously.

Inventive Principle:
Principle #3Local quality

3Productivity

If traditional material handling mechanisms are used to move food, then the productivity is improved, but the food quality (texture and taste) is degraded

Engineering Contradiction:
Improvefood assembly speedVSAvoidfood texture and taste alteration
Core Design Contradiction:
ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent applies parameter changes by adjusting velocity and acceleration parameters dynamically during food handling operations. By controlling these motion parameters to remain below threshold values, the robot prevents mechanical damage to food while maintaining efficient assembly speeds, thus resolving the contradiction between productivity and food quality.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11597084B2Controlling robot torque and velocity based on context
Publication Date: 2023.03.07 DEXAI ROBOTICS INC
  • US11597084B2 patent drawing
  • US11597084B2 patent drawing
  • US11597084B2 patent drawing

AI summary

In an embodiment, a method includes identifying a force and torque for a robot to accomplish a task and identifying context of a portion of a movement plan indicating motion of the robot to perform the task. Based on the identified force, torque, and context, a context specific torque is determined for at least one aspect of the robot while the robot executes the portion of the movement plan. In turn, a control signal is generated for the at least one aspect of the robot to operate in accordance with the determined context specific torque.