SBIR-STTR Award

Many modern approaches to autonomy use a layered planning technique where a conventional path planner plans a nominal desired path, and a reactive planner plans trajectories over a local region. In relatively structured environments with good localization, this layered approach has been proven to work well, as shown by TORC’s successful 3rd place entry in the 2007 DARPA Urban Challenge. The overall goal of this Phase I SBIR program is to develop new planning algorithms that allow operation in environments with dynamic obstacles, and do not depend on idealized sensors or accurate global localization. TORC proposes to evaluate two distinct approaches during this Phase I feasibility study. The first approach will use new Rapidly Exploring Dense Tree (RDT/RRT)-based techniques to plan among possible actions. The second approach extends our previous success in the Urban Challenge by creating time indexed costs based on forward simulations of object behavior. This augmented cost map will leverage the ease of representation and searching trajectories, and provide a method of including object motion.

Keywords:
Path Planning, Autonomous, Dynamic Environment, Gps-Denied, Darpa Urban Challenge

This research focuses on providing a capability to perform rapid, semi-autonomous unmanned assessment of potential combat airstrips. Current Tactics Techniques and Procedures require the operator to walk the runway and manually assess viability. Soil hardness measurements are sampled manually along with marking of hazards to flight, which may occur along the runway as well as along approach and takeoff vectors. To gain data of high quality and maximize mission success, operations are conducted at night in the shortest possible timeframe required. The objective is to automate and shorten time required to produce the airfield survey data product by providing an autonomous system capable of surveying a 3,500-foot expedient runway in less than 90 minutes, in day and night conditions, reducing risk to operators on assault zone survey missions and increasing survey product quality.

Benefit:
Unmanned Ground Vehicles have shown promise enhancing a number of military missions; however most successful autonomous systems perform in highly structured environments. To enable operations in militarily relevant, unstructured environments at an operational tempo, a number of obstacle avoidance and planning challenges must be overcome. A viable autonomous system should require minimal supervisory control and operate across a variety of environments from off-road cross-country terrain to dynamic urban environments. The enhanced behaviors and perception capabilities integrated under this effort to support the expedient airfield survey mission will further the goal of enabling operations in military relevant dynamic environments. Commercial applications of this technology include the dull, dirty or dangerous tasks in the agriculture, mining or security markets. The high reliability and system ruggedness needed for the airfield survey system will be a major step towards the requirements for the commercial market.

Keywords:
Runway Assessment, Assault Zone Survey, Terminal Evaluation Kit