Autonomous Trailer Hitching via Neural Network Gesture Control

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Tow vehicle drivers face challenges when connecting to trailers, requiring multiple people to guide the vehicle into position, which can be inefficient and unsafe, especially for those unfamiliar with the hitching process.

Innovation Solution

A method for autonomously maneuvering a vehicle in reverse to attach to a trailer using a computing device with a neural network, cameras, and a drive system, allowing for user input gestures to control the vehicle's path and suspension adjustments for alignment with the trailer hitch.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual hitching guidance is used with multiple people, then the hitching process can be completed, but it requires additional personnel and reduces efficiency

Engineering Contradiction:

Improvehitching efficiencyVSAvoidpersonnel requirement

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The hitching system performs self-guidance by using its own sensors (cameras, LIDAR, ultrasonic sensors) to detect the trailer and compute the hitching path autonomously, eliminating the need for external personnel to guide the vehicle during hitching operations

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical human-guidance system with an automated sensor-based detection and control system that uses neural networks and path computation algorithms to guide the vehicle hitching process

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If manual hitching guidance is used, then the driver can receive directions, but it creates safety risks for unfamiliar users

Engineering Contradiction:

Improvehitching safetyVSAvoiduser familiarity requirement

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system provides self-guidance through automated trailer detection and path computation, allowing any user regardless of familiarity to safely perform hitching operations without needing experienced personnel to provide directions

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system continuously provides feedback to the driver through the user interface, displaying detected trailer positions, computed paths, and real-time guidance information, enabling users to safely perform hitching without prior experience

Inventive Principle:

Principle #23Feedback

3Speed

If autonomous trailer detection is implemented, then hitching speed increases, but the system complexity increases

Engineering Contradiction:

Improvehitching speedVSAvoidsensor system complexity

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The autonomous detection system is divided into separate functional modules: sensor subsystem (cameras, LIDAR, ultrasonic sensors), processing subsystem (neural network for trailer detection), and control subsystem (path computation and vehicle control), allowing complex functionality to be achieved through coordinated simpler components

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10884425B2Autonomous trailer hitching using neural network

Publication Date: 2021.01.05 CONTINENTAL AUTONOMOUS MOBILITY US LLC

AI summary

One aspect of the disclosure provides a method of maneuvering a vehicle in reverse for attachment to a trailer. The method includes: determining, at a computing device in communication with the neural network, a selected trailer in proximity to the vehicle; detecting at least one user input gesture performed by a user and captured in at least one image from at least one camera on the vehicle; selected a maneuver command for the vehicle based on the detected gesture; and executing the maneuver to move the vehicle from the initial position toward a final position adjacent the trailer.