Interpret Goal States in Motor System & Switch Policies
Enable the motor system to switch between different ways to achieve goals.
We would like to implement a state-switching mechanism where the motor system can switch the policy that it is executing, depending on the goal it receives.
For example, we might want to do a semi-random walk when the motor system is not receiving goals. We may want to switch to a saccade policy (rotating the sensor without moving it's position) when the sensor module sends a goal based on detected salient features.
This task also relates to Enable Switching Between Learning and Inference-Focused Policies.
Help Us Make This Page Better
All our docs are open-source. If something is wrong or unclear, submit a PR to fix it!
Updated 16 days ago