The objective of our research is to enable underwater robots to autonomously maintain their position, follow along fixed natural and artificial features, search in regular patterns, and ultimately, to swim after dynamic targets. These capabilities are essential to tasks like cataloging reefs, exploring geologic features, and studying marine creatures, as well as inspecting pipes and cables, and assisting divers.

In the Underwater Robotics project, we are developing an autonomous underwater vehicle, named Kambara, so that we can discover effective means of accomplishing these tasks. Kambara is self-sufficient, with onboard computing, sensing, and power resources. Our research is to develop low-level servo-control and high-level behaviors, to autonomously perform exploration and inspection tasks underwater.

Learned Control
Many approaches have been taken to the problem of motion control for underwater vehicles, ranging from traditional control to modern control to variety of neural network-based architectures. Most existing systems control limited motions yet require detailed dynamic models of the vehicle and a number of simplifying assumptions which may limit its operating regime and/or robustness. This result is expensive, sensitive, and unsatisfactory.

We seek an alternative. We are developing a method by which Kambara learns to control its own motions directly from experience of its actions in the world. Kambara starts with no explicit models of itself or of the effect that any action may produce. Our method uses a connectionist (artificial neural network) implementation of model-free reinforcement learning. Kambara learns in response to a reward signal, attempting to maximize its total reward over time, as it converges on a correct mapping from how it wishes to move to what specific action it should take.

Underwater Visual Servo-control
Controlling its own motion is part of the AUV's challenge, another is autonomously determining where to go. To guide itself, Kambara is equipped with color video cameras, video digitizers and a real-time computing system. Although not without difficulties underwater, we are investigating color stereo perception because of the availability of detectable features and the importance of visual cues to the tasks we envision for Kambara.

We use visual information, not to build maps to navigate, but for visual-servo control. We apply techniques for correlation-based feature tracking in a hierarchical matching scheme to track features from frame to frame. Correlating visual features from two separate cameras enables Kambara to triangulate the distance to the feature.

The motion of the visual features between images directly guides the motion of the AUV, just as you use the motion the road edge to help you adjust the steering of your car. We are currently implementing simple behaviors to regulate position and velocity relative to visual features. In this manner we intend Kambara to hold station on a reef, swim along a pipe, perform a repeatable search of the sea floor.

Students are a vital part of our project and their individual projects contribute necessary component and algorithm development to our overall program.


Enable Kambara to autonomously:
  • Observe dynamic visual features
  • Follow along static visual features
  • Search in a regular pattern
  • Swim after dynamic targets
  • Applications

    In order to ground our research and keep the various (undergraduate, graduate, and postgraduate) projects relevant to real problems, we envision a number of applications for this work.

    Marine Biology
    Observe natural structures like coral reefs to measure growth and change
    Return to sites over time or under varying conditions to observe change
    Observe many animals to determine population or group behavior
    Follow individual creatures to observe behavior

    Marine Geology
    Survey and mapping of underwater structures
    Follow precise transects of the sea floor
    Repeated observation of dynamic geologic features

    Underwater Inspection
    Perform anomaly detection on cables, pipes, piers, rigs, and other artificial structures
    Maintain a fixed position and orientation in rough seas (station keeping)

    Underwater Assistant
    Follow diver automatically, maintaining safe standoff
    Avoid obstacles including other divers
    Dive to depths beyond diver's limit to make observations/locate dropped objects

    Kambara Project at the ANURobotic Systems Laboratory
    By David Wettergreen<dsw@syseng.anu.edu.au>
    Last modified: