Robotics II: Possible Projects

• Design your own: Suggest a project that is interesting to you. As long as it is challenging and related to the class topics, I will probably approve it. It is my belief that you and I will both get more out of the class if your project is closely aligned with your interests. The IEEE Robotics and Automation Magazine is a good source of ideas; volume 14, number 1, (March 2007) is focused on "Grand Challenges of Robotics."

• Grasp acquisition: Perform grasp selection with GraspIt! Then execute the grasp with the Barrett Hand. Compare results.

• Grasp acquisition under uncertainty: Implement algorithm to choose grasps, then attempt to achieve grasp in simulation using dVC. Inject error and see how errors effect grasp achievement.

• Caging: Develop control algorithms for multiple robots to surround and transport an object. Study size of disturbing force for object to escape the cage.

• Metamorphic robots: Create components that dock and undock and plan shape-changing tasks, e.g., create a tank tread or open loop and cause it to locomote over uneven terrain.

• Push planning I: Plan pushing actions in a horizontal plane with obstacles. Goal is to move an object from a given initial configuration to a goal configuration with a paddle-type pusher. Lynch's work is relevant.

• Push planning II: Plan pushing actions in a horizontal plane with obstacles. Goal is to move an object from a given initial configuration to a goal configuration using a needle-like pusher. This is inspired by Kumar's micro-manipulation work.

• Automated handling of shipping containers: Develop planner for automated handling of shipping containers.

• Vibratory self-assembly: Vibratory potential fields might be used in the manipulation and assembly of tiny parts. Implement existing algorithm in dVC.

• Build and test a robot grasper: A planar hand would be sufficient. Would be great to simulate in dVC and compare simulated and experimental results.

• Build a test a Pachinko machine: Build a Pachinko-like machine. The idea would be to be to determine how to place pins so that a part of a given geometry would always reach the bottom in a chosen configuration. Use dVC for testing. If multiple people are involved, expand the scope of the project to include parameter estimation from part trajectory data gathered with a camera.

• Two-Handed planar assembly: Build two arms and grippers in dVC and then develop a controller to assemble two parts.

• Add a feature to dVC: For example, create code to format output from dVC for Matlab.