Objective
The objective of this project is to demonstrate underwater robotic localization, characterization, and precise excavation of partially buried inert munitions using the SHARC (SHared Autonomy for Remote Collaboration) robotic framework. This technology will be adapted to provide real-time three-dimensional (3D) workspace situational awareness when operating in turbid coastal environments that are currently infeasible using conventional robotic manipulation and machine vision techniques. Demonstrations will include multiple remote operators and observers collaborating simultaneously.
Technical Approach
The technical approach of this project will consist of three main elements: (1) modify an existing robotic manipulator arm in the project team's lab to operate with a wrist-mounted ultra-high frequency imaging sonar and jet/vacuum excavation tool, (2) develop a real-time process that fuses SHARC’s existing optical imagery-based 3D workspace visualization with sonar acoustic perception, (3) conduct operations tests to evaluate the utility of the modified SHARC system for localization, characterization, and excavation of partially-buried inert munitions in optically turbid water.
Benefits
SHARC is platform independent and can be readily integrated into underwater and terrestrial platforms equipped with at least one robotic manipulator, workspace imaging sensor, and data link to the operators. SHARC’s task allocation process delegates responsibilities between the robot and operator based on their complementary strengths. Human operators are responsible for high-level scene understanding, goal selection (e.g., identifying sample locations), and task-level planning, which are challenging for existing perception and decision-making algorithms. These tasks are particularly difficult to automate in cluttered and unstructured environments typical of unexploded ordnance mitigation operations. Meanwhile, SHARC automates robotic processes that can readily be solved using autonomy algorithms. By automating the inverse kinematics, motion planning, low-level control, and obstacle avoidance processes to the robot, SHARC can improve task efficiency. Critically, SHARC renders the robot’s intended actions (e.g., the planned trajectory of the arm) prior to execution in context of its understanding of the surrounding environment (e.g., a 3D scene reconstruction along with the location and label of detected tools), thereby making its behavior more predictable than conventional interfaces. With this task allocation approach, operators no longer need to simultaneously interpret the robot’s many high-frequency sensor streams while solving the lowlevel manipulator kinematics necessary to move the end-effector. Instead, these tasks are offloaded to the robot, which reduces the operators’ cognitive burden. The inherent flexibility and intuitive nature of the SHARC interface enables users to collaborate simultaneously and succinctly issue complex commands that would otherwise be time-consuming and difficult to execute with conventional controllers. Within a matter of seconds, remote users can safely specify and execute a robotic task that would normally require many minutes when using a conventional interface.
(Anticipated Project Completion - 2025).