Vehicle control based on perception uncertainty

Abstract

Aspects of the disclosure relate generally to maneuvering autonomous vehicles. Specifically, the vehicle (101) may determine the uncertainty in its perception system and use this uncertainty value to make decisions about how to maneuver the vehicle. For example, the perception system may include sensors (310-311, 321-323, 330-331), object type models, and object motion models (146), each associated with uncertainties. The sensors may be associated with uncertainties based on the sensor's range, speed, and / or shape of the sensor field (421A-423A, 421B-423B). The object type models may be associated with uncertainties, for example, in whether a perceived object is of one type (such as a small car) or another type (such as a bicycle). The object motion models may also be associated with uncertainties, for example, not all objects will move exactly as they are predicted to move. These uncertainties may be used to maneuver the vehicle.

Description

[0001] Cross References to Related Applications [0002] This application is a continuation of US Patent Application No. 13 / 361,083, filed January 30, 2012, the disclosure of which is hereby incorporated by reference. Background technique [0003] Autonomous vehicles use various computing systems to help transport passengers from one location to another. Some autonomous vehicles may require initial or continuous input from an operator, such as a navigator, a driver, or passengers. Other autonomous systems such as autopilot systems that allow the operator to switch from a manual mode (in which the operator exercises a high degree of control over the movement of the vehicle) to an autonomous mode (in which the vehicle is primarily driven by itself) may be used only if the system is already in use ) to switch to the mode in between. [0004] Such vehicles are equipped with vehicle perception systems that include various types of sensors to detect objects in the surrounding envi...

AI Technical Summary

Problems solved by technology

For example, camera sensors do not directly measure distance, laser sensors do not directly measure speed, radar sensors do not measure the shape of objects, etc.

Additionally, sensors may have limited range, frame rate, noise pattern, etc.

All of these constraints can lead to "uncertainty" in the perception of the world

Images