Can I use experience in Game AI development to develop autonomous driving robots? How much similar this areas?


Depending on what you mean by experience...While you have been developing GameAI I assume you gained domain specific and domain independent experience:

  • Theoretical AI knowledge is key to all applications from Game AI to Autonomous Driving, but the knowledge has to be abstract and not domain dependent. Decision making, reinforcement learning, search, symbolic planning are all AI methods for solving domain problems, some of which can apply to autonomous driving also.
  • Game design experience can be limitedly reused for simulation environment design for autonomous robots.
  • Managing large datasets is a common trait for all supervised learning applications, I'd imagine there are some stricter rules for handling large datasets for autonomous driving but this experience should be domain independent.
  • Deployment: I'd guess not, deployment for GameAI, in my opinion is very different from deployment of autonomous driving
  • Maintenance same as deployment.

This playlist should give you a good intro on autonomous driving and you can see for yourself what part have you experience with already.

EDIT: Based on your comment below, Search algorithms using navmesh for path finding does not have much in common with autonomous driving. Steering behaviours might come in handy in for implementing driving simulation environments if they can closely reflect reality. Locomotion...again in simulated environments simulated humans have to move around somehow, but this is not directly related to autonomous driving.

| improve this answer | |
  • $\begingroup$ I mean Pathfinding, Steering, Locomotion, atc. Game AI algorithms $\endgroup$ – Robotex Nov 7 '19 at 15:13

Not the answer you're looking for? Browse other questions tagged or ask your own question.