Robot Motion Control Using Fused State and Environmental Parameters

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The control of robots is typically achieved through fixed program instructions, leading to inadequate adaptation to their environment, resulting in low motion performance.

Innovation Solution

A robot control method that involves acquiring state and environmental data, predicting initial and environmental impact parameters, and fusing them to generate a control instruction that adapts the robot's actions to both the environment and the target object's actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If fixed program instructions are used to control the robot, then the control system is simple and reliable, but the robot cannot accurately adapt to the environment, resulting in low motion performance

Engineering Contradiction:
Improveenvironmental adaptationVSAvoidcontrol system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The control system transitions from static fixed program instructions to dynamic adaptive control. The robot uses neural network models that continuously learn and adjust control parameters based on environmental feedback, enabling the system to adapt its behavior dynamically to match environmental characteristics while maintaining manageable complexity through modular architecture.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The robot employs self-supervised learning mechanisms where it autonomously learns environmental characteristics and adjusts its own control parameters without external intervention. The system performs self-adaptation by processing environmental data through trained neural networks to generate appropriate control instructions, reducing the need for complex pre-programming while improving environmental adaptation.

Inventive Principle:
Principle #25Self-service

2Productivity

If fixed program instructions are used to control the robot, then the control method is simple, but the motion performance is low due to inability to adapt to environment

Engineering Contradiction:
Improvemotion performanceVSAvoidcontrol method complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary learning and training of neural network models before actual robot operation. Environmental data is pre-processed and used to train the control model, so that when the robot executes tasks, it already possesses adapted control parameters. This preliminary action enables high motion performance during execution while keeping the real-time control method relatively simple.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces traditional mechanical control methods (fixed program instructions) with intelligent software-based control (neural network models). This substitution allows the system to achieve high motion performance through adaptive algorithms rather than complex mechanical adjustments, improving productivity while managing complexity through software intelligence.

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

Data Source

PatentEP4678350A1Robot control method and apparatus, and electronic device, computer-readable storage medium and computer program product
Publication Date: 2026.01.14 TENCENT TECHNOLOGY (SHENZHEN) CO LTD
  • EP4678350A1 patent drawingFigure 1~2
  • EP4678350A1 patent drawingFigure 3~5
  • EP4678350A1 patent drawingFigure 6~7

AI summary

Provided are a robot control method and apparatus, an electronic device, a storage medium, and a program product. The method includes: acquiring state data configured for indicating a current motion state of a robot, and acquiring environmental data configured for indicating an environment where the robot is currently located; predicting, based on the state data, an initial action parameter configured for controlling the robot to imitate an object action of a target object; predicting, based on the environmental data, an environmental impact parameter configured for representing impact generated by the environment on imitation of the object action by the robot; fusing the initial action parameter and the environmental impact parameter to obtain a fused action parameter of the robot; and generating a control instruction based on the fused action parameter, the control instruction being configured for controlling the robot to perform a target action indicated by the fused action parameter.