Strange-looking result with rule-based controller

NeLy-EPFL / flygym

Simulating embodied sensorimotor control with NeuroMechFly v2

https://neuromechfly.org/

Apache License 2.0

26 stars 7 forks source link

Strange-looking result with rule-based controller #186

Closed sibocw closed 4 months ago

sibocw commented 4 months ago

After various refactoring, the flygym/examples/locomotion/rule_based_controller.py script on the dev-v1.0.0-pre.4 branch currently produces the following results. It looks a bit strange to me. What do you think @stimpfli @tkclam

Should we migrate the code to run the controller benchmark from nmf2-paper to flygym/examples to facilitate checking things like this?

https://github.com/NeLy-EPFL/flygym/assets/23410765/d01310ea-d178-417b-9d4e-0b30eec7d96b

sibocw commented 4 months ago

Results normal; benchmarking code merged from nmf2-paper to flygym/examples. See #184.