Autonomous Vehicle Environment Discretization for Real-Time Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for autonomous vehicle control face challenges in achieving efficient and robust real-time operation due to impractical solutions in discretization, leading to high computational complexity and performance loss, especially when handling objects with varying resolutions.

Innovation Solution

A multivariable discretization method is employed to represent the vehicle's environment, using offline and online resources to determine a quasi-optimal discretization function, minimizing computational cost while maintaining accurate object representation, by iteratively refining the discretization process through heuristic and sampling or gradient descent methods.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If high resolution discretization is used to maintain accurate object representation, then manufacturing precision is improved, but device complexity increases

Engineering Contradiction:
Improveobject representation accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent applies different discretization resolutions to different spatial regions based on their importance. Objects closer to the ego vehicle or more critical for safety decisions are represented with higher resolution, while distant or less critical objects use lower resolution. This local differentiation maintains necessary accuracy for important objects while reducing overall computational complexity.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The discretization resolution is made dynamic and adaptive rather than static. The system adjusts the discretization level based on real-time factors such as object distance, relative velocity, object type, and predicted trajectory. This allows the system to allocate computational resources dynamically, maintaining high precision when needed while reducing complexity during normal operation.

Inventive Principle:
Principle #15Dynamics

2Manufacturing precision

If continuous approach to world model is used without discretization, then manufacturing precision is improved, but productivity decreases

Engineering Contradiction:
Improveworld model accuracyVSAvoidreal-time processing capability
Core Design Contradiction:
Manufacturing precisionVSProductivity

Solution Approach 1:

The patent transforms the continuous world model parameters into discrete representations through adaptive discretization. By changing the parameter representation from continuous to discrete based on importance metrics, the system maintains sufficient accuracy for decision-making while enabling efficient computational processing in real-time.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If drastic discretization is applied to reduce data processing amount, then productivity is improved, but manufacturing precision deteriorates

Engineering Contradiction:
Improvedata processing efficiencyVSAvoidobject representation accuracy
Core Design Contradiction:
ProductivityVSManufacturing precision

Solution Approach 1:

Instead of uniform drastic discretization, the patent applies selective discretization where only non-critical objects or regions undergo aggressive discretization. Critical objects maintain higher precision representation, ensuring that productivity gains do not compromise safety-relevant accuracy.

Inventive Principle:
Principle #3Local quality

4Device complexity

If multi-resolution approach is used for spatial discretization, then device complexity is reduced, but adaptability deteriorates

Engineering Contradiction:
Improvecomputational complexityVSAvoidhandling objects with varying resolutions
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic multi-resolution system that adapts to different object types, distances, and scenarios. The discretization strategy is not fixed but adjusts based on environmental context, object importance, and safety requirements, thereby maintaining high adaptability while benefiting from reduced complexity through selective resolution levels.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3792124B1Method for controlling an autonomous vehicle including discretisation of data from the environment
Publication Date: 2025.12.03 RENAULT SA
  • EP3792124B1 patent drawingFigure 1~3
  • EP3792124B1 patent drawingFigure 4
  • EP3792124B1 patent drawing

AI summary

A method for controlling an autonomous vehicle to determine the final position of the autonomous vehicle in an environment comprising at least one object as a function of the initial position of the vehicle, comprising the following steps: - A state vector is determined for each object in the environment comprising at least one value acquired by the autonomous vehicle as a function of measurements taken by at least one sensor of the autonomous vehicle, - Discretized state vectors are determined by applying a discretization function to each state vector, the discretization function being defined by at least one set of parameters determined beforehand, - The displacement of the autonomous vehicle from the initial position of the vehicle to a final position is determined by applying a driving function to the discretized state vectors of the objects in the environment, - The autonomous vehicle is controlled to reach the final position by the determined displacement.