Deterministic Motion Planning With Dispersion-Optimized Sampling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Probabilistic sampling-based motion planners for autonomous agents yield stochastic results, making formal verification and validation challenging in safety-critical applications, while deterministic approaches are limited to specific Euclidean spaces and systems.

Innovation Solution

A deterministic sampling-based motion-planning algorithm that optimizes sample node selection using a dispersion criterion to minimize the largest uncovered area, ensuring obstacle-free paths and improved planning efficiency and path quality, employing a PRM* or FMT* algorithm with a steering function to define movement constraints.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If probabilistic sampling-based motion planners are used, then exploration of configuration space is improved, but deterministic performance and formal verification are worsened

Engineering Contradiction:

Improveexploration capabilityVSAvoiddeterministic performance

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent replaces the probabilistic random sampling mechanism with a deterministic quasi-Monte Carlo sampling approach using low-discrepancy sequences. This substitution maintains the exploratory capability of random sampling while eliminating stochastic variability, enabling deterministic performance bounds and formal verification for safety-critical applications.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the sampling distribution from uniform random sampling to a structured low-discrepancy sequence sampling. By modifying the parameterization of sample generation from stochastic to deterministic sequences with guaranteed distribution properties, the system achieves both good space exploration and deterministic performance guarantees.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If deterministic state sets are used, then certification process is improved, but applicability to complex systems is worsened

Engineering Contradiction:

Improvecertification easeVSAvoidapplicability range

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal sampling framework based on low-discrepancy sequences that can be applied to diverse systems including robotic manipulators, mobile robots, and autonomous vehicles. The deterministic sampling approach with configurable dimensionality and space adaptation enables broad applicability across different system types while maintaining certification-friendly deterministic behavior.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11872703B2Method and device for deterministic sampling-based motion planning

Publication Date: 2024.01.16 ROBERT BOSCH GMBH

AI summary

A computer-implemented method for planning an optimized motion path. The optimized motion path is determined applying a sampling-based motion-planning algorithm depending on a sample node set including sample nodes. The sample nodes in the sample node set are deterministically selected from a configuration node set including all obstacle free nodes. The sample nodes are selected to optimize a given dispersion criterion. The dispersion criterion selects the sample nodes so that the largest uncovered area/space within the configuration node set is as small as possible.