Autonomous Vehicle Object Size Adjustment for Collision Avoidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in accurately determining the size and position of forward objects due to limitations in sensor resolution and orientation, which can lead to inadequate driving maneuvers and potential collisions.

Innovation Solution

A method and system that determine a size adjustment factor to predict the laterally innermost point of detected objects, using sensor data to adjust for uncertainties and improve driving maneuvers, involving the use of a processor and sensor system to analyze shape profiles and calculate size factors for precise object detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If sensor resolution and orientation are used to detect objects, then object detection capability is improved, but measurement precision of object size and position deteriorates due to sensor limitations

Engineering Contradiction:
Improveobject detection capabilityVSAvoidobject size and position accuracy
Core Design Contradiction:
Difficulty of detecting and measuringVSMeasurement precision

Solution Approach 1:

The patent changes the parameters of object detection by determining a size adjustment factor based on the detected shape profile of the object. Instead of relying solely on raw sensor data, the system adjusts the perceived size parameters of the object to account for sensor resolution limitations and orientation effects, thereby improving measurement precision while maintaining detection capability

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent introduces an intermediary computational step by determining a size adjustment factor that mediates between the raw sensor detection data and the final object size/position measurements. This adjustment factor acts as a corrective intermediary that compensates for sensor limitations without requiring hardware changes

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If size adjustment factor is determined to predict laterally innermost point, then driving maneuver accuracy is improved, but computational complexity increases

Engineering Contradiction:
Improvedriving maneuver accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies local quality by determining the size adjustment factor specifically for the laterally innermost point of the object rather than uniformly adjusting all object parameters. This localized approach improves driving maneuver accuracy at the critical inner boundary while minimizing unnecessary computational overhead for other object parameters

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent performs preliminary action by determining the size adjustment factor and predicting the laterally innermost point before executing the driving maneuver. This advance computational preparation allows the vehicle to plan safe trajectories in advance, improving maneuver accuracy while organizing computations efficiently to manage complexity

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9616886B2Size adjustment of forward objects for autonomous vehicles
Publication Date: 2017.04.11 TOYOTA JIDOSHA KK
  • US9616886B2 patent drawing
  • US9616886B2 patent drawing
  • US9616886B2 patent drawing

AI summary

Systems and methods relating to the operation of an autonomous vehicle relative to forward objects in an external environment are described. At least a forward portion of the external environment can be sensed to detect an object therein. A size adjustment factor can be determined to predict a laterally innermost point of the detected object relative to the autonomous vehicle. A driving maneuver for the autonomous vehicle can be determined based at least partially on the predicted laterally innermost point of the detected object relative to the autonomous vehicle.