Occupancy-Grid Path Planning for Unstructured Vehicle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face navigation challenges when pathway indicators such as runway lights, lane markings, or traffic signs are obscured, degraded, or invalidated, leading to inefficient or inaccurate navigation in unstructured environments.
Innovation Solution
An autonomous vehicle guidance system that generates paths based on an occupancy map, using a grid overlay and precomputed motion primitives, allowing the vehicle to navigate even without clear indicators by determining collision-free and low-cost trajectories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous vehicles rely on pathway indicators such as runway lights, lane markings, and traffic signs for navigation, then navigation accuracy is improved under normal conditions, but navigation reliability deteriorates when indicators are obscured, degraded, or invalidated
Solution Approach 1:
The patent introduces an occupancy map as an intermediary representation that translates complex visual pathway indicators into a simplified grid-based model of free space and obstacles. This mediator allows the vehicle to navigate by referencing the occupancy map rather than directly interpreting potentially obscured or degraded visual indicators, thereby maintaining navigation reliability when traditional indicators are compromised
Solution Approach 2:
The patent replaces the mechanical/visual system of relying on physical pathway indicators (lane markings, lights, signs) with a computational system that generates paths based on occupancy maps and motion primitives. This substitution enables the vehicle to navigate unstructured environments where traditional visual indicators are absent or unreliable, improving overall navigation reliability
2Device complexity
If the vehicle uses traditional path planning methods based on pathway indicators, then computational simplicity is maintained, but adaptability to unstructured environments deteriorates
Solution Approach 1:
The patent segments the continuous navigation problem into discrete components: the environment is divided into a grid-based occupancy map, motion is represented as discrete motion primitives (e.g., straight, left turn, right turn), and path planning becomes a sequence selection problem. This segmentation maintains computational simplicity while enabling adaptability to unstructured environments by allowing the system to generate paths without relying on pre-defined pathway indicators
Solution Approach 2:
The patent changes the fundamental parameters of path planning from indicator-based coordinates to occupancy-based grid cells and motion primitives. By transforming the navigation problem into selecting sequences of motion primitives that move the vehicle through free space in the occupancy map, the system achieves both computational simplicity and adaptability to diverse environments
3Reliability
If the vehicle continuously generates paths using occupancy maps and motion primitives, then navigation reliability in unstructured environments is improved, but computational load increases
Solution Approach 1:
The patent performs preliminary computation by pre-defining a finite set of motion primitives that represent all feasible vehicle movements. By having these motion sequences pre-computed and stored, the system reduces real-time computational load to merely selecting and sequencing appropriate primitives based on the current occupancy map, rather than computing all possible paths from scratch
Solution Approach 2:
The patent implements dynamic path re-planning by continuously updating the occupancy map and regenerating paths as the vehicle moves and the environment changes. The system dynamically adjusts the sequence of motion primitives based on real-time occupancy information, maintaining navigation reliability while managing computational load through efficient reuse of pre-computed primitives
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An autonomous vehicle guidance system that generates a path for controlling an autonomous vehicle based at least in part on a data structure generated based at least in part on sensor data that may indicate occupied space in an environment surrounding an autonomous vehicle. The guidance system may receive a grid and generate a grid associated with the grid and the data structure. The guidance system may additionally or alternatively sub-sample the grid (latterly and/or longitudinally) dynamically based at least in part on characteristics determined from the data structure. The guidance system may identify a path based at least in part on a set of precomputed motion primitives, costs associated therewith, and/or a heuristic cost plot that indicates a cheapest cost to move from one pose to another.