Skip to main content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Identifying Sensory Processing Requirements for an On-Road Driving Application of 4D/RCS

Published

Author(s)

John A. Horst, Anthony J. Barbera, Craig I. Schlenoff, David Aha

Abstract

A key challenge when applying architectures to real-time intelligent control problems is defining the hardware requirements for their sensory processing tasks.  Identifying these tasks is also difficult, necessitating a detailed task analysis and performance metrics for the resulting system.  For applications of NIST's Real-time Control System (RCS, now referred to as 4D/RCS) (Albus et al., 2002), this requires drilling down from its control modules to its world modeling primitives.  We describe an example of this process for our On-Road Driving project, where our goal is to design, implement, and evaluate a 4D/RCS application for controlling the behaviors of an autonomous vehicle that is maneuvering through common on-road driving situations.  We briefly review the 4D/RCS design methodology and reference architecture, and our design for applying it to this task, including our task decomposition representation format for on-road driving task knowledge.  We use this representation to further specify the world model entities, attributes, features, and events required for proper reasoning about each of the subtask activities.  In turn, we use these world model specifications to identify the requirements for the sensory processing system (i.e., objects that have to be measured in the environment, including their resolutions, accuracy tolerances, detection timing, and detection distances for each subtask activity).  We describe our project's task and world modeling knowledge, and a set of performance metrics for validating sensory processing activities by evaluating the world model representations the system produces for each individual component subtask activity. We also detail our approach for two subtasks  passing a vehicle and maneuvering about objects while following a
Citation
NIST Interagency/Internal Report (NISTIR) - 7167
Report Number
7167

Keywords

4D/RCS, autonomous vehicle, hierarchical control, on-road driving, performance metrics, sensory processing, task decomposition, world modeling
Created January 4, 2006, Updated November 10, 2018