Autonomous Vehicle Command Control for Smooth Multi-Object Navigation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing autonomous vehicle systems face challenges in navigating complex environments with multiple static and dynamic objects and conditions, often resulting in abrupt acceleration or deceleration due to over- or under-estimation of object impacts, leading to an unpleasant ride and safety concerns.

Innovation Solution

The system employs a computing device that determines vehicle control commands, such as acceleration and steering, by considering a plurality of objects and conditions using sensor data and multiple command controllers, which generate and prioritize control requests based on velocity, distance, and time information, allowing for more accurate and efficient navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the vehicle control system responds to multiple objects and environmental conditions with high sensitivity, then the safety and accuracy of navigation are improved, but the vehicle may exhibit abrupt acceleration or deceleration due to over-estimation of object impacts

Engineering Contradiction:
Improvesafety of navigationVSAvoidpassenger comfort
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The control system is divided into multiple independent command controllers (first command controller, second command controller, third command controller), each responsible for different aspects of vehicle control (e.g., stop control, follow control, speed limit control). This segmentation allows each controller to operate independently with optimized parameters, preventing abrupt responses while maintaining overall safety through coordinated control commands.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If the vehicle control system uses a single control command for navigation, then the system complexity is reduced, but the accuracy of determining safe speeds and optimizing vehicle control is insufficient in complex environments

Engineering Contradiction:
Improveaccuracy of safe speed determinationVSAvoidcontrol system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Multiple command controllers generate individual control commands that are merged into a single coordinated control output. The system combines stop control commands, follow control commands, and speed limit control commands from different controllers, weighting and integrating them to produce an optimized final control decision that maintains high accuracy without excessive complexity.

Inventive Principle:
Principle #5Merging (Combining)

3Reliability

If the vehicle control system responds aggressively to detected objects to ensure safety, then the reliability of collision avoidance is improved, but the ride quality deteriorates due to abrupt acceleration or deceleration

Engineering Contradiction:
Improvecollision avoidanceVSAvoidride quality
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system dynamically adjusts control parameters such as weighting factors and response thresholds based on environmental context and object characteristics. By changing parameters adaptively, the system can prioritize safety when collisions are imminent while maintaining smooth ride quality during normal operation, resolving the contradiction between aggressive safety responses and comfortable ride quality.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3911548B1Vehicle control
Publication Date: 2024.04.03 ZOOX INC
  • EP3911548B1 patent drawingFigure 1
  • EP3911548B1 patent drawingFigure 2
  • EP3911548B1 patent drawingFigure 3

AI summary

Command determination for controlling a vehicle, such as an autonomous vehicle, is described. In an example, individual requests for controlling the vehicle relative to each of multiple objects or conditions in an environment are received (substantially simultaneously) and based on the request type and/or additional information associated with a request, command controllers can determine control commands (e.g., different accelerations, steering angles, steering rates, and the like) associated with each of the one or more requests. The command controllers may have different controller gains (which may be based on functions of distance, distance ratios, time to estimated collisions, etc.) for determining the controls and a control command may be determined based on the all such determined controls.