Open af-a opened 4 years ago
How do we expect the robot to find the obstacle? Is it manually set?
For now, we assume that the scene has been perceived, so the positions and bounding boxes of obstacles are known. In the long run, we would like to react to dynamic obstacles as well.
The first point was addressed in #231.
Problem description
The current DMP-based implementation of the move arm action uses open-loop, naive trajectory generation, which does not take obstacles into account. For example, if the robot attempts to pick an object off of a table, it will simply reproduce the given trajectory, regardless of whether that would cause the end-effector to collide with other obstacles on that table. This is not ideal in such cases and may lead to task failures.
Desired solution
The DMP formulation enables an effective obstacle avoidance strategy, discussed in detail in this publication, by adding an appropriate term in the differential equation governing the evolution of the variable (end-effector position). Implementing this could be enhance the move arm action with real-time obstacle avoidance, assuming that the robot can perceive the positions of obstacles with reasonable accuracy.
Suggested courses of action:
Future