TRACLabs engineers have developed intelligent control architectures that provide robust autonomy to robotic platforms. These architectures combine reactivity with deliberation to accommodate both real-time closed-loop control and long-range planning and execution of tasks. Our approach emphasizes adjustable autonomy whereby a human operator can easily intervene at any level of robot operation. TRACLabs personnel have extensive experience with control of highly dynamic manipulation systems.
Layered Control Architectures
TRACLabs Inc. researchers invented the layered approach to controlling robotic systems. This software is called 3T because it has three interacting layers (or tiers) of control—one for low-level robot control, one for sequencing basic robot operations and one for planning robotic resource and time constraints.
A sensor-to-symbol architecture regularizes the connections between the sensed physical world and the symbols that represent that world. TRACLabs Inc. is building, under DARPA contract, a sensor-to-symbol architecture. The architecture can watch various sensory streams and match the outputs of simple or complex sensory algorithms onto ontological classes.
TRACLabs Inc. engineers have developed advanced process control systems for NASA life support system tests over the past ten years. These tests range from a two-year integrated water recovery system test to a 90-day human test of an integrated life support system. TRACLabs Inc. software controlled test hardware via high-level, goal-directed commanding to maintain system stability and respond to faults. TRACLabs Inc. engineers have expertise in extracting domain knowledge from hardware developers and encoding that knowledge in control software.
Procedure Assistance Software
Intelligent, Electronic Procedures
TRACLabs Inc. has been developing procedure assistance support software for over a decade. TRACLabs personnel invented the Procedure Representation Language (PRL), which is an XML schema that allows the content of a procedure to be captured for possible automated execution. TRACLabs personnel have also worked on the Procedure Integrated Development Environment (PRIDE), a procedure authoring tool being developed by NASA’s Automation for Operations (A4O) program to make developing PRL easier for flight controllers.
Procedure Representation Language (PRL)
PRL is an XML schema developed by TRACLabs Inc. that deﬁnes a variety of tags that can be used to describe a procedure. At the highest level is a procedure tag that marks the beginning of a new procedure. Each procedure consists of steps that describe smaller tasks within the procedure. Steps themselves have blocks that are containers for instructions that provide explicit detail about commanding a system. Each of these components can have automation data that controls their execution status.
TRACLabs Inc. software engineers are developing automated planning software to assist operations planners in creating schedules that optimize time and resources. Our operations planning assistant is interactive and allows for changes in crew schedules, tool availability and time allotments. Prototypes of this planning assistant tool are being developed for ISS EVA operations and ISS PHALCON operations. The planning assistant is designed to work with the Procedure Representation Language (PRL) also developed by TRACLabs researchers.
The planning problem is to determine a state sequence to achieve desired goal state(s) given an initial state(s). An automated planner is a type of general problem solver that accepts a high-level problem description and computes its solution. TRACLabs Inc. is developing automated planners for NASA and military applications.
Learn more about Metrica’s research projects at www.traclabs.com.