Defense Advanced Research Projects AgencyTagged Content List

Supervised Autonomy

Automated capabilities with human supervision; "human in the loop"

Showing 84 results for Autonomy + Unmanned RSS
The U.S. military’s investments in unmanned aircraft systems (UAS) have proven invaluable for missions from intelligence, surveillance and reconnaissance (ISR) to tactical strike. Most of the current systems, however, require constant control by a dedicated pilot and sensor operator as well as a large number of analysts, all via telemetry. These requirements severely limit the scalability and cost-effectiveness of UAS operations and pose operational challenges in dynamic, long-distance engagements with highly mobile targets in contested electromagnetic environments.
In the latest step in a decades-long process through which automation has taken on increasing responsibilities in the cockpit—allowing pilots to focus on flight tasks demanding their unique capabilities—DARPA has awarded three contracts for its Aircrew Labor In-Cockpit Automation System (ALIAS) program. ALIAS envisions a tailorable, drop-in, removable kit that would enable high levels of automation in existing aircraft and facilitate reduced need for onboard crew. The program intends to leverage the considerable advances that have been made in aircraft automation systems over the past 50 years, as well as the advances that have been made in remotely piloted aircraft technologies, to help shift and refocus pilot workloads, augment mission performance and improve aircraft safety.
DARPA’s Anti-Submarine Warfare (ASW) Continuous Trail Unmanned Vessel (ACTUV) program seeks to develop a new type of unmanned surface vessel that could independently track adversaries’ ultra-quiet diesel-electric submarines over thousands of miles. One of the challenges that the ACTUV program is addressing is development of autonomous behaviors for complying with the International Regulations for Preventing Collisions at Sea, known as COLREGS. Substantial progress has been made in developing and implementing those behaviors.
They may not have zoomed flawlessly around obstacles like the Millennium Falcon did as it careened through the hull of a crashed Star Destroyer in Star Wars VII. But the sensor-loaded quadcopters that recently got tested in a cluttered hangar in Massachusetts did manage to edge their way around obstacles and achieve their target speeds of 20 meters per second. Moreover, the quadcopters were unmanned … and real. Thus was the initial phase of data collection for DARPA's Fast Lightweight Autonomy (FLA) program recently deemed an encouraging success.
A research effort associated with DARPA’s Aircrew Labor In-Cockpit Automation System (ALIAS) program recently conducted the first successful flight tests of a shoebox-sized, plug-and-play system designed to enable manned and unmanned aircraft to automatically detect nearby aircraft and avoid potential mid-air collisions. An unmanned air vehicle (UAV) repeatedly used the technology demonstration system to detect and track in real time a Cessna 172G aircraft approaching from various vertical and horizontal distances.