A recent talk discussed ethics for autonomous vehicles, as an optimization problem. There can be several imperatives for an AV which are all “correct”, yet be in conflict for an autonomous vehicle which relies on hard coded logic.
For example: Follow Traffic safety rules. Stick to the lane. Avoid obstacles. Save most human lives. Save passengers.
How can a vehicle prioritize these ? Instead of a case by case design, the proposal is to cast it in an ethics framework based on optimization of various ideals and constraints with weighted coefficients. Then test the outcomes.
The optimization equation looks to minimize ( path_tracking + steering + traffic_laws ) subject to constraints ( avoid_obstacles ). The equations produce different behaviour when the coefficients are changed.
Another consideration is the Vehicle intent: is it fully in control or can the human override it. This affects the software assumptions and system design.
The talk was presented by Sarah Thornton, PhD. Stanford. A related discussion on safety is here : Who gets the blame when driverless cars crash ?.
Somewhat related is the idea of computer vision itself operating correctly. There can be adversarial inputs as discussed in the paper Intriguing properties of neural networks which discusses blind spots. Generative Adversarial Models are a way to improve the generalization capabilities of a network by pitting generative against discriminative models. The European Conference on Computer Vision starts today: http://www.eccv2016.org/main-conference/