Autonomous Vehicle Response Control for Unknown Road Objects

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current autonomous vehicle technologies respond uniformly to unknown objects on the carriageway, leading to unnecessary or excessive disruptions in traffic flow, as they lack the ability to tailor responses based on the object's characteristics and location.

Innovation Solution

A control subsystem that processes sensor data to determine the size and location of unknown objects, defining motion plans such as changing lanes, slowing, or stopping, to ensure safety and efficiency in navigation, thereby minimizing disruption to traffic flow.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If autonomous vehicles respond uniformly to all unknown objects, then safety is maintained through consistent caution, but traffic flow disruption increases due to unnecessary or excessive responses

Engineering Contradiction:
ImprovesafetyVSAvoidtraffic flow
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system applies different response strategies to different unknown objects based on their local characteristics (size, location). Instead of uniform treatment, the motion planning module tailors the vehicle's response to each object's specific properties, allowing cautious behavior for small objects and more aggressive avoidance for large objects, thereby maintaining safety while reducing unnecessary traffic disruption

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system dynamically adjusts the motion plan based on real-time assessment of object characteristics. The response strategy changes from static uniform caution to dynamic adaptation where the vehicle's behavior (lane change, slowing, stopping) is determined by the specific properties of each detected object, optimizing both safety and traffic flow efficiency

Inventive Principle:
Principle #15Dynamics

2Reliability

If autonomous vehicles maintain large distance from all unknown objects, then safety is improved, but navigation efficiency decreases due to excessive caution

Engineering Contradiction:
ImprovesafetyVSAvoidnavigation efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system determines the appropriate safety distance based on the local characteristics of each unknown object. For small objects like stones, the vehicle maintains minimal distance and may proceed over them. For large objects, the vehicle maintains larger distance and executes avoidance maneuvers. This localized adaptation of safety margins optimizes both safety and navigation efficiency

Inventive Principle:
Principle #3Local quality

3Measurement precision

If autonomous vehicles classify objects by size and location, then response accuracy improves, but system complexity increases

Engineering Contradiction:
Improveresponse accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the classification process into distinct stages: detection, size determination, location determination, and motion plan definition. Each stage handles a specific aspect of object assessment, making the overall complex process more manageable and systematic. The segmentation allows the system to build response accuracy through progressive refinement without overwhelming complexity

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses parameter changes (size and location) as the basis for determining the appropriate motion plan. By focusing on these specific measurable parameters rather than attempting to identify all possible object characteristics, the system achieves accurate responses while keeping the complexity manageable through parameter-based decision making

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4249342B1Control subsystem and method to define the response of an autonomous vehicle to an unknown object
Publication Date: 2024.11.06 TUSIMPLE INC
  • EP4249342B1 patent drawingFigure 1~2
  • EP4249342B1 patent drawingFigure 3
  • EP4249342B1 patent drawingFigure 4A

AI summary

A control subsystem (20), method, computer program product and autonomous vehicle (102, 10) are provided to respond to an unknown object (16) on a carriageway (12) along which an autonomous vehicle (102, 10) is to travel. In this regard, sensor data is received from at least one vehicle sensor (116). The sensor data includes location coordinates of the object (16) on the carriageway (12). The sensor data is evaluated to determine whether the object (16) is known or unknown. If unknown, the size of the object (16) is determined and a motion plan is defined for the autonomous vehicle (102, 10) depending upon the size of the object (16) and the location coordinates of the object (16) relative to the autonomous vehicle (102, 10). The motion plan that is defined is dependent upon the size of the object with different motion plans being defined for differently sized objects. Driving instructions for the autonomous vehicle (102, 10) are then updated based upon the motion plan that is defined.