Robot Touch Feedback Using IMU-Based Force Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Smart robots struggle to accurately execute feedback events due to external factors affecting their anthropomorphism, as they cannot reliably discern the force and type of user interactions through conventional tactile sensors.

Innovation Solution

Incorporating an inertial measurement unit (IMU) and touch sensors on the robot to detect changes in heading angle in response to user interactions, allowing the robot to determine the force and type of operation based on offset angles, enabling precise execution of corresponding control events.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the robot uses only touch sensors to recognize operations, then the device complexity is low, but the measurement precision of operation force is insufficient

Engineering Contradiction:
Improveoperation force detectionVSAvoidsensor system
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an inertial measurement unit (IMU) as an intermediary device to indirectly measure operation force. Instead of using complex force sensors directly on the touch surface, the IMU detects changes in robot body acceleration and orientation caused by user operations, converting mechanical interactions into measurable inertial data. This intermediary approach enables force detection without direct mechanical contact sensors.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional mechanical force sensors with an inertial measurement system. By substituting direct mechanical measurement with inertial sensing (accelerometers, gyroscopes), the system achieves force detection capability while reducing mechanical complexity. The IMU converts mechanical operation forces into electrical signals through inertial effects, eliminating the need for complex mechanical force transduction mechanisms.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If the robot adds IMU and multiple sensors to improve anthropomorphism, then the measurement precision of external factors improves, but the device complexity increases

Engineering Contradiction:
Improveanthropomorphism degreeVSAvoidsensor system
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent makes the IMU serve multiple functions: detecting operation force, determining operation direction, and identifying operation intensity. A single IMU device replaces what would otherwise require multiple specialized sensors, achieving versatile operation recognition (force, direction, intensity) while minimizing the increase in device complexity. The multi-functional use of the IMU enables comprehensive anthropomorphic feedback without proportionally increasing system complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent combines multiple sensing capabilities (acceleration detection, orientation detection, force inference) into a single integrated IMU system. By merging these functions into one device rather than using separate sensors for each parameter, the system achieves high adaptability for recognizing various operation types while keeping the overall sensor system compact and manageable.

Inventive Principle:
Principle #5Merging (Combining)

3Reliability

If the robot uses touch sensors alone, then the ease of operation is maintained, but the reliability of control event execution deteriorates

Engineering Contradiction:
Improvecontrol event executionVSAvoidoperation recognition
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent implements feedback by continuously monitoring IMU data during user operations and using this information to adjust and confirm operation recognition. The system compares expected operation patterns with actual IMU measurements, providing feedback validation that enhances the reliability of control event execution. This feedback mechanism ensures that operations are correctly interpreted even in ambiguous situations.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent performs preliminary analysis of IMU data to predict operation type and force before finalizing control event execution. By pre-processing and analyzing inertial measurement data in advance, the system can prepare appropriate responses and validate operation intentions, improving the reliability of subsequent control event execution without complicating the user interaction process.

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution enhances the robot's ability to accurately respond to user interactions by considering factors like force, location, and operation type, thereby improving anthropomorphism.

Implementation Method 1

an inertial measurement unit (IMU) is mounted in the robot... the IMU is configured to collect a heading angle of the robot

Methodology Applied
Scientific EffectInertial measurement: Accelerometer

Data Source

PatentUS12420432B2Robot feedback method and robot
Publication Date: 2025.09.23 HUAWEI TECH CO LTD
  • US12420432B2 patent drawing
  • US12420432B2 patent drawing
  • US12420432B2 patent drawing

AI summary

A robot feedback method includes that an IMU is mounted in the robot, a plurality of first preset regions are provided with a touch sensor, the touch sensor is configured to collect an operation acting on the robot, and the IMU is configured to collect a heading angle of the robot. The robot receives a first operation acting on a first region of the first preset regions. In addition, the robot obtains location information of the first region, an operation type of the first operation, and a first offset reflecting a force of the first operation acting on the robot. Then the robot executes a first control event corresponding to the location information of the first region, the operation type of the first operation, and the force of the first operation acting on the robot.