Autonomous Travel Direction Control for Dynamic Hazard Response

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems for autonomous or semiautonomous units, such as robots and vehicles, face challenges in accurately determining their direction of travel in dynamically changing environments, particularly in hazardous situations where external objects pose an immediate threat, due to limitations in predicting and reacting to spontaneous movements.

Innovation Solution

A method involving independent execution of movement prediction and determination algorithms using surrounding-area parameters to ascertain probabilistic and short-term movement parameters, allowing for rapid and reliable control, including emergency collision prevention and pathfinding, to ensure safe navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If a single integrated algorithm is used for movement prediction and determination, then the system structure is simpler, but the system cannot react rapidly enough to hazardous situations and computing resources are not optimized

Engineering Contradiction:
Improvereaction speed to hazardous situationsVSAvoidalgorithm structure complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent divides the movement analysis system into two independent algorithms: a movement prediction algorithm for general future path prediction and a movement determination algorithm for immediate hazard response. This segmentation allows each algorithm to be optimized for its specific function, enabling rapid reaction to hazardous situations while maintaining manageable system complexity through modular design.

Inventive Principle:
Principle #1Segmentation

2Reliability

If probabilistic movement prediction is performed for all external objects, then the system can plan future paths, but computing expenditure increases significantly

Engineering Contradiction:
Improvepath planning reliabilityVSAvoidcomputing energy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies different levels of analysis to different external objects based on their relevance to the unit's future path. Probabilistic movement prediction is performed selectively for objects that may intersect with the planned path, while less critical objects receive simpler determination algorithm analysis. This local differentiation optimizes computing energy consumption while maintaining path planning reliability.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If the movement determination algorithm uses output from the movement prediction algorithm, then the system can leverage predictive information, but the determination of immediate short-term movement is slowed down

Engineering Contradiction:
Improvemovement parameter accuracyVSAvoidcomputation time for immediate response
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts the immediate short-term movement determination from the probabilistic prediction process. The movement determination algorithm independently calculates short-term movement parameters for rapid hazard response without waiting for the slower probabilistic prediction algorithm to complete its analysis. This extraction enables timely reactions to hazardous situations while still achieving accurate movement parameter determination through independent algorithmic analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS20240123982A1Method for ascertaining a direction of travel of an at least semiautonomously or autonomously movable unit, and device or system
Publication Date: 2024.04.18 ROBERT BOSCH GMBH
  • US20240123982A1 patent drawing
  • US20240123982A1 patent drawing
  • US20240123982A1 patent drawing

AI summary

A method for ascertaining a direction of travel and/or a future path of travel of a robot and/or a vehicle, movable at least semiautonomously or autonomously in a dynamically changeable surrounding area. The method includes: measuring and/or ascertaining surrounding-area parameters, which may each be assigned to at least one moving, external object in the area surrounding the unit; executing at least one movement prediction algorithm for ascertaining, in each instance, at least one probabilistic movement prediction parameter for detected external objects as a function of measured surrounding-area parameters assigned to the individual external objects; executing at least one movement determination algorithm for ascertaining at least one short-term movement parameter for each detected external objects as a function of measured surrounding-area parameters assigned to the individual external objects; the movement prediction algorithm and the movement determination algorithm being executed at least substantially independently of each other.