Robot Path Optimization Using Footprint Contours for Smooth Obstacle Avoidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robot path planning methods fail to achieve smoothness and optimal obstacle avoidance simultaneously, particularly for small and symmetrical robots, as they often rely on centroid-based obstacle distance optimization which is inadequate.

Innovation Solution

A method and apparatus for iteratively optimizing the initial robot path by determining smoothness and obstacle costs using footprint contours, adjusting path points based on smoothness and obstacle gradients, and incorporating nearest obstacle distances into an objective function to achieve a more reasonable and smooth obstacle avoidance path.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If centroid-based obstacle distance optimization is used for small and symmetrical robots, then the obstacle avoidance capability is improved, but the path smoothness deteriorates

Engineering Contradiction:
Improveobstacle avoidance capabilityVSAvoidpath smoothness
Core Design Contradiction:
ReliabilityVSShape

Solution Approach 1:

The robot body is segmented into multiple sections along its longitudinal direction, with each section having its own optimization coordinates. This segmentation allows different parts of the robot to be optimized independently for both obstacle avoidance and path smoothness, resolving the contradiction between these two requirements.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The optimization approach transitions from 2D centroid-based coordinates to 3D body section-based coordinates. By introducing the vertical dimension (body sections) and using spatial coordinates relative to each section, the method achieves more comprehensive optimization that simultaneously improves obstacle avoidance and path smoothness.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Shape

If numerical optimization is applied to optimize the initial path, then the path smoothness is improved, but the computational complexity increases

Engineering Contradiction:
Improvepath smoothnessVSAvoidcomputational complexity
Core Design Contradiction:
ShapeVSDevice complexity

Solution Approach 1:

The path optimization problem is segmented into multiple sub-problems, each corresponding to a specific body section. By dividing the overall optimization into section-level optimizations with localized coordinates, the computational complexity is reduced while maintaining path smoothness through coordinated optimization of all sections.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Each body section has its own local coordinate system and optimization parameters. This local quality approach allows optimization to be performed independently at each section level, reducing the overall computational burden while ensuring global path smoothness through the coordination of all local optimizations.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4290328B1Path optimization method and apparatus, and robot and storage medium
Publication Date: 2025.09.17 JD DIGITS HAIYI INFORMATION TECHNOLOGY CO LTD
  • EP4290328B1 patent drawingFigure 1
  • EP4290328B1 patent drawingFigure 2
  • EP4290328B1 patent drawingFigure 3

AI summary

A method and an apparatus (8) for path optimization, a robot (9) and a storage medium. The method includes: acquiring (S101) an initial path of a robot (9), and iteratively optimizing the initial path based on the following steps until a preset iteration termination condition is met to obtain obstacle avoidance path of the robot (9); acquiring (S102) an iteration path corresponding to a current iteration process, determining a smoothness cost corresponding to the iteration path and a smoothness optimal gradient corresponding to an iteration path point in the iteration path; determining (S103) a robot's (9) footprint contour corresponding to the iteration path point, and searching for a first nearest obstacle distance corresponding to the footprint contour; determining (S104) an obstacle cost corresponding to the iteration path and an obstacle optimal gradient corresponding to the iteration path point based on the first nearest obstacle distance; adjusting (S105) the iteration path point based on the smoothness optimal gradient and the obstacle optimal gradient to acquire an iteration path corresponding to a next iteration process; inputting (S106) the smoothness cost and the obstacle cost to a preset objective function.