Robot Route Specification with Constraint Regions for Obstacle Adaptation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional robotic navigation systems lack the necessary context to effectively navigate constrained environments, leading to unsafe and inefficient path execution due to the loss of high-level navigation information at the local level, particularly when encountering dynamic obstacles.

Innovation Solution

A route specification language that includes context and constraints, such as goal regions and constraint regions, is used to generate a series of route segments for robotic navigation, allowing local navigation systems to make informed decisions and optimize paths while maintaining safety and efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If conventional robotic navigation systems operate at local level without high-level context, then device complexity is reduced, but navigation safety and effectiveness deteriorate

Engineering Contradiction:
Improvenavigation system complexityVSAvoidnavigation safety
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The navigation system is divided into hierarchical levels: high-level navigation generates route specifications with constraints and goal regions, while local-level navigation executes path following. This segmentation allows each level to operate independently with appropriate complexity, while the high-level context ensures safety and effectiveness through constraint regions that guide local navigation decisions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Route specifications serve as an intermediary data structure that transfers high-level navigation intent to the local navigation system. These specifications include constraint regions, goal regions, and path segments that encode safety requirements and mission objectives, enabling local navigation to make informed decisions without directly processing complex high-level planning logic.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Manufacturing precision

If robotic navigation systems follow strict initial paths, then navigation precision is improved, but adaptability to dynamic obstacles deteriorates

Engineering Contradiction:
Improvepath following precisionVSAvoiddynamic obstacle handling
Core Design Contradiction:
Manufacturing precisionVSAdaptability or versatility

Solution Approach 1:

The navigation system implements dynamic path adjustment by allowing local navigation to deviate from initial paths when obstacles are detected. Constraint regions define acceptable deviation boundaries, enabling the robot to adapt to dynamic obstacles while maintaining overall path accuracy. The system dynamically balances following the planned path versus avoiding obstacles based on real-time sensor input.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4139764B1Constrained robot autonomy language
Publication Date: 2025.07.02 BOSTON DYNAMICS INC
  • EP4139764B1 patent drawingFigure 1
  • EP4139764B1 patent drawingFigure 2
  • EP4139764B1 patent drawingFigure 3

AI summary

A method for constraining robot autonomy language includes receiving a navigation command (44) to navigate a robot (10) to a mission destination (46) within an environment (8) of the robot and generating a route specification (200) for navigating the robot from a current location (43) in the environment to the mission destination in the environment. The route specification includes a series of route segments (210). Each route segment in the series of route segments includes a goal region (220) for the corresponding route segment and a constraint region (230) encompassing the goal region. The constraint region establishes boundaries for the robot to remain within while traversing toward the goal region. The route segment also includes an initial path (310) for the robot to follow while traversing the corresponding route segment.