General Motors has filed a patent for a driver training system which uses a vehicle’s in-vehicle sensing equipment to determine how well a novice motorist behaves behind the wheel.
The goal is to provide driver training without the help of a real-life instructor. Instead, the self-driving vehicle limits the amount of control offered to the student while constantly monitoring their progress. If they score high enough, further freedom is given to the driver and the process begins again – this time with the vehicle looking to assess more advanced maneuvers while keeping an eye on the basics. It’s a little different from the usual practice of having someone sit next to you to take stock of your budding riding skills. But GM thinks it could have future applications and probably wants to lock it down with the United States Patent and Trademark Office (USPTO) before anyone else.
This is corroborated by the very generalized language used in the record, first shared by Engine1. While we have no doubt that the company (and probably a few others) have been working on the concept of a computer-controlled driving instructor, there’s not much in the abstract. There’s also a soup of words in the summary with plenty of wiggle room for implementation. The brief casts a wide net on how this system would actually work, likely as a way to hedge in terms of design variation. But that’s pretty standard for USPTO filings.
From the summary:
According to an exemplary embodiment, a method is provided for training a trainee using an autonomous vehicle, the method comprising; measuring, via one or more sensors, one or more manual inputs from the trainee concerning the control of the autonomous vehicle; determining, via a processor using an autonomous driving algorithm stored in a memory of the autonomous vehicle, one or more recommended actions for the autonomous vehicle; comparing, via the processor, the trainee’s manual input(s) with one or more actions recommended for this autonomous vehicle, generating a comparison; and determining, via the processor, a score for the trainee based on comparing the trainee’s manual input(s) with the recommended action(s) for the autonomous vehicle.
It’s almost tragic that people who work in the patent office have to read stuff like this all day and I’m sincerely sorry that you just had to spend a while in their shoes. But the bottom line is that GM has come up with a concept and would like to keep it in check before one of its rivals comes up with something similar.
The automaker says the supposed benefits include eliminating any instructor bias and reducing the cost of existing training programs. Theoretically, this could be a feature that General Motors simply builds into future products (assuming self-driving cars one day become mainstream), sells via an over-the-air update, or lends to driving schools. As a by-product, the system could also accumulate value-generating data for the business. As for the hardware required, GM left things pretty vague. However, the document refers to camera arrays, lidar and global positioning systems (GPS) that have been integrated into vehicles as potential solutions. Other than that, the cars should have an on-board processor to assess the trainee’s progress and maintain their own self-driving capabilities.
But the automaker admitted there could be some blind spots, including the possibility that a human driver might need to assume full control of an autonomous vehicle on occasion. This includes cases where some sensing equipment is damaged or obscured and whenever the car is on an unmapped road it does not know how to navigate.
[Image: Demskoy Studio/Shutterstock]
Become a TTAC insider. Get the latest TTAC news, features, takes, and all things truth about cars first subscribe to our newsletter.