Autonomous Vehicle Torque-Based Obstacle Detection at Initial Motion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles are insensitive to non-moving objects and have difficulty detecting obstacles during initial motion, particularly when parked and starting from a standstill, which can lead to accidents or damage.
Innovation Solution
A vehicle detection system that measures and compares the predicted propulsion and steering torque required to move the vehicle with actual torque values, using locally or remotely stored reference values, to detect obstructing objects during initial motion at low speeds, and initiates actions such as braking or alerting the user if deviations exceed a threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous driving systems use standard sensors (radar, computer vision, Lidar) to detect objects, then they can detect moving objects and traffic situations, but they become insensitive to non-moving objects and less sensitive during initial motion of the vehicle
Solution Approach 1:
The system performs preliminary detection actions before the vehicle starts moving by measuring torque values during the initial motion phase. This preliminary action allows the system to detect obstructing objects that would otherwise be missed by standard sensors during standstill or initial motion, thereby improving detection reliability across all motion states.
Solution Approach 2:
The patent introduces torque measurement as an intermediary parameter to detect obstructing objects. Instead of relying solely on standard sensors that fail during initial motion, the system uses torque data from the propulsion system as a mediator to indirectly detect the presence of objects, thus expanding detection versatility.
2Use of energy by moving object
If the vehicle is parked and autonomous driving systems are shut down to save energy, then energy consumption is reduced, but the vehicle becomes vulnerable and cannot detect objects positioned around or underneath it
Solution Approach 1:
The system uses the vehicle's own propulsion system torque measurements to perform safety detection during initial motion, eliminating the need for separate active sensing systems during parked state. This self-service approach allows the vehicle to detect obstructing objects using existing components, maintaining safety without significant additional energy consumption.
3Productivity
If the vehicle starts moving without detecting obstructing objects, then it can begin operation, but it risks hitting objects and causing damage
Solution Approach 1:
The system performs preliminary torque-based detection during the initial motion phase before the vehicle commits to full operation. This preliminary check ensures that obstructing objects are identified early, allowing the system to prevent movement or alert the operator, thus eliminating collision risk while maintaining operational readiness.
Solution Approach 2:
The system continuously monitors torque values during initial motion and compares them against expected ranges. This feedback mechanism allows real-time detection of abnormal conditions indicating obstructing objects, enabling the system to respond appropriately by preventing movement or alerting the operator, thus resolving the conflict between operational readiness and collision risk.
Data Source
Figure 1
Figure 2a~2e
Figure 3
AI summary
The present invention relates to a vehicle adapted for autonomous driving, such as an autonomous vehicle, comprising an assisting object detecting system for detecting obstructing objects to the vehicle (1). The object detecting system is adapted to detect an object by comparing a reference value of a selected parameter with a measured value of the selected parameter. The present invention also relates to a method and a computer program product for use in the vehicle.