Existing control techniques often assume access to complete dynamics or perfect simulators with fully observable states, which are necessary to verify whether the system remains within a safe set (forward invariance) or safe actions are persistently feasible at all times. However, many systems contain latent variables that make their dynamics partially unidentifiable or cause distribution shifts in the observed statistics between offline and online data, even when the underlying mechanistic dynamics are unchanged. Such “spurious” distribution shifts can break many techniques that use data to learn system models or safety certificates. To address this limitation, we propose a technique for designing probabilistic safety certificates for systems with latent variables. A key technical enabler is the formulation of invariance conditions in probability space, which can be constructed using observed statistics in the presence of distribution shifts due to latent variables. We use this invariance condition to construct a safety certificate that can be implemented efficiently in real-time control. The proposed safety certificate can persistently find feasible actions that control long-term risk to stay within tolerance. Stochastic safe control and (causal) reinforcement learning have been studied in isolation until now. To the best of our knowledge, the proposed work is the first to use causal reinforcement learning to quantify long-term risk for the design of safety certificates. This integration enables safety certificates to efficiently ensure long-term safety in the presence of latent variables. The effectiveness of the proposed safety certificate is demonstrated in numerical simulations.

Safe control methods are often designed to behave safely even in worst-case human uncertainties. Such design can cause more aggressive human behaviors that exploit its conservatism and result in greater risk for everyone. However, this issue has not been systematically investigated previously. This paper uses an interaction-based payoff structure from evolutionary game theory to model humans’ short-sighted, self-seeking behaviors. The model captures how prior human-machine interaction experience causes behavioral and strategic changes in humans in the long term. We then show that deterministic worst-case safe control techniques and equilibrium-based stochastic methods can have worse safety and performance trade-offs than a basic method that mediates human strategic changes. This finding suggests an urgent need to fundamentally rethink the safe control framework used in human-technology interaction in pursuit of greater safety for all.

This paper presents an adaptive safe control method that can adapt to changing environments, tolerate large uncertainties, and exploit predictions in autonomous driving. We first derive a sufficient condition to ensure long-term safe probability when there are uncertainties in system parameters. Then, we use the safety condition to formulate a stochastic adaptive safe control method. Finally, we test the proposed technique numerically in a few driving scenarios. The use of long-term safe probability provides a sufficient outlook time horizon to capture future predictions of the environment and planned vehicle maneuvers and to avoid unsafe regions of attractions. The resulting control action systematically mediates behaviors based on uncertainties and can find safer actions even with large uncertainties. This feature allows the system to quickly respond to changes and risks, even before an accurate estimate of the changed parameters can be constructed. The safe probability can be continuously learned and refined. Using more precise probability avoids over-conservatism, which is a common drawback of the deterministic worst-case approaches. The proposed techniques can also be efficiently computed in real-time using onboard hardware and modularly integrated into existing processes such as predictive model controllers.