Autonomous Vehicle Drive Envelope for Multi-Agent Path Planning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional planning systems for vehicles often consider individual agents discretely, leading to less than optimal efficiency and passenger comfort due to the lack of consideration for multiple agents in determining actions or reactions while traveling, resulting in segmented travel paths.

Innovation Solution

The development of a drive envelope that considers multiple agents, including dynamic and static obstacles, using sensor data and probabilistic information to determine safe trajectories for autonomous vehicles, allowing for efficient navigation by encoding complex environmental data into a single representation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If conventional planning systems consider individual agents discretely, then the system complexity is reduced, but the navigation efficiency and passenger comfort deteriorate

Engineering Contradiction:
Improvesystem complexityVSAvoidnavigation efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent merges multiple individual agent considerations into a unified drive envelope representation. Instead of processing each agent separately, the system combines all agent positions, velocities, and predicted trajectories into a single composite safety boundary that encompasses all obstacles, thereby reducing computational complexity while maintaining comprehensive safety analysis.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The drive envelope serves multiple functions simultaneously: it acts as a safety boundary, a navigation guide, and a collision avoidance zone. This universal representation replaces multiple separate processing functions that would otherwise be needed for individual agent analysis, improving efficiency without sacrificing safety.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Ease of operation

If conventional systems determine actions based on individual agents, then the decision-making process is simplified, but the passenger comfort and satisfaction worsen

Engineering Contradiction:
Improvedecision-making simplicityVSAvoidpassenger comfort
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The system combines the effects of multiple agents on passenger comfort into a single drive envelope boundary. This allows the decision-making process to remain simple (checking whether the path stays within the envelope) while implicitly considering the cumulative impact of all agents on comfort, as the envelope is constructed to maintain optimal spacing from all obstacles simultaneously.

Inventive Principle:
Principle #5Merging (Combining)

3Use of energy by moving object

If discrete consideration of individual agents is used, then computational resources are conserved, but the travel path optimization deteriorates

Engineering Contradiction:
Improvecomputational resourcesVSAvoidtravel path optimization
Core Design Contradiction:
Use of energy by moving objectVSProductivity

Solution Approach 1:

The patent merges all agent data into a single drive envelope structure that can be processed efficiently. By representing multiple agents as one composite boundary rather than multiple separate entities, the system reduces the computational burden of path optimization while still achieving optimal travel paths that consider all obstacles collectively.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The drive envelope creates a simplified copy or abstraction of the complex multi-agent environment. This virtual representation captures the essential safety and optimization constraints without requiring detailed processing of each individual agent, enabling efficient path planning with reduced computational resources.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3794572B1Drive envelope determination
Publication Date: 2024.08.28 ZOOX INC
  • EP3794572B1 patent drawingFigure 1
  • EP3794572B1 patent drawingFigure 2
  • EP3794572B1 patent drawingFigure 3

AI summary

Drive envelope determination is described. In an example, a vehicle can capture sensor data while traversing an environment and can provide the sensor data to computing system(s). The sensor data can indicate agent(s) in the environment and the computing system(s) can determine, based on the sensor data, a planned path through the environment relative to the agent(s). The computing system(s) can also determine lateral distance(s) to the agent(s) from the planned path. In an example, the computing system(s) can determine modified distance(s) based at least in part on the lateral distance(s) and information about the agents. The computing system can determine a drive envelope based on the modified distance(s) and can determine a trajectory in the drive envelope.