Browse Prior Art Database

Diagnostics Mechanism for Self-Driving Cars to validate Self-Driving Capabilities

IP.com Disclosure Number: IPCOM000237171D
Publication Date: 2014-Jun-06
Document File: 4 page(s) / 52K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a secondary, independent system that is built into a self-driving car to monitor aspects of the vehicle’s movement and validate that the performance is correct for self-driving mode.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 01 of 4

Diagnostics Mechanism for Self-Driving Cars to validate Self-Driving Capabilities

Self-driving cars communicate with other vehicles to indicate whether in the self-driving or manual driving mode. This is similar to an identification, friend, or foe (IFF) system in military warfare.

This status identification system has the potential for misrepresentation due to system malfunction . A system/tool must be created to validate that the system is working as intended and has not been damaged or altered. A method is needed to ensure cars are able to accurately identify which cars are self-driven vs. those that are currently set in manual mode.

The novel contribution is a secondary, independent system that is built into a self-driving car to validate correct functionality. As the car travels, the system gathers data, such as speed, acceleration, steering corrections, wheel changes, deceleration, and gear changes through sensors in various points in the car. Using this data, the secondary system determines if the car is currently in a self-driving mode or a manual driving mode. The system compares the collected data to the car's settings. For instance, self-driving cars travel at a consistent speed and with course checks, but a manually driven car tends to fluctuate in its speed and handling. If there is a discrepancy between the setting and the actual current function, then the system generates or records an alert.

Depending on the implementation, various levels of certainty can be built into the system to validate whether the secondary system must be 100% correct, or if warnings could be emitted with less certai...