An official website of the United States government
As humans interact with autonomous agents to perform increasingly complicated, potentially risky tasks, it is important to be able to efficiently evaluate an agent’s performance and correctness. In this paper we formalize and theoretically analyze the problem of efficient value alignment verification: how to efficiently test whether the behavior of another agent is aligned with a human’s values. The goal is to construct a kind of “driver’s test” that a human can give to any agent which will verify value alignment via a minimal number of queries. We study alignment verification problems with both idealized humans that have an explicit reward function as well as problems where they have implicit values. We analyze verification of exact value alignment for rational agents and propose and analyze heuristic and approximate value alignment verification tests in a wide range of gridworlds and a continuous autonomous driving domain. Finally, we prove that there exist sufficient conditions such that we can verify exact and approximate alignment across an infinite set of test environments via a constant- query-complexity alignment test.
more »
« less
Risk of Stochastic Systems for Temporal Logic Specifications
The wide availability of data coupled with the computational advances in artificial intelligence and machine learning promise to enable many future technologies such as autonomous driving. While there has been a variety of successful demonstrations of these technologies, critical system failures have repeatedly been reported. Even if rare, such system failures pose a serious barrier to adoption without a rigorous risk assessment. This article presents a framework for the systematic and rigorous risk verification of systems. We consider a wide range of system specifications formulated in signal temporal logic (STL) and model the system as a stochastic process, permitting discrete-time and continuous-time stochastic processes. We then define the STL robustness risk as the risk of lacking robustness against failure . This definition is motivated as system failures are often caused by missing robustness to modeling errors, system disturbances, and distribution shifts in the underlying data generating process. Within the definition, we permit general classes of risk measures and focus on tail risk measures such as the value-at-risk and the conditional value-at-risk. While the STL robustness risk is in general hard to compute, we propose the approximate STL robustness risk as a more tractable notion that upper bounds the STL robustness risk. We show how the approximate STL robustness risk can accurately be estimated from system trajectory data. For discrete-time stochastic processes, we show under which conditions the approximate STL robustness risk can even be computed exactly. We illustrate our verification algorithm in the autonomous driving simulator CARLA and show how a least risky controller can be selected among four neural network lane-keeping controllers for five meaningful system specifications.
more »
« less
- Award ID(s):
- 2038873
- PAR ID:
- 10441191
- Publisher / Repository:
- ACM Transactions on Embedded Computing Systems
- Date Published:
- Journal Name:
- ACM Transactions on Embedded Computing Systems
- Volume:
- 22
- Issue:
- 3
- ISSN:
- 1539-9087
- Page Range / eLocation ID:
- 1 to 31
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We propose an automatic synthesis technique to generate provably correct controllers of stochastic linear dynamical systems for Signal Temporal Logic (STL) specifications. While formal synthesis problems can be directly formulated as exists-forall constraints, the quantifier alternation restricts the scalability of such an approach. We use the duality between a system and its proof of correctness to partially alleviate this challenge. We decompose the controller synthesis into two subproblems, each addressing orthogonal concerns - stabilization with respect to the noise, and meeting the STL specification. The overall controller is a nested controller comprising of the feedback controller for noise cancellation and an open loop controller for STL satisfaction. The correct-by-construction compositional synthesis of this nested controller relies on using the guarantees of the feedback controller instead of the controller itself. We use a linear feedback controller as the stabilizing controller for linear systems with bounded additive noise and over-approximate its ellipsoid stability guarantee with a polytope. We then use this over-approximation to formulate a mixed-integer linear programming (MILP) problem to synthesize an open-loop controller that satisfies STL specifications.more » « less
-
This article introduces a model-based approach for training feedback controllers for an autonomous agent operating in a highly non-linear (albeit deterministic) environment. We desire the trained policy to ensure that the agent satisfies specific task objectives and safety constraints, both expressed in Discrete-Time Signal Temporal Logic (DT-STL). One advantage for reformulation of a task via formal frameworks, like DT-STL, is that it permits quantitative satisfaction semantics. In other words, given a trajectory and a DT-STL formula, we can compute therobustness, which can be interpreted as an approximate signed distance between the trajectory and the set of trajectories satisfying the formula. We utilize feedback control, and we assume a feed forward neural network for learning the feedback controller. We show how this learning problem is similar to training recurrent neural networks (RNNs), where the number of recurrent units is proportional to the temporal horizon of the agent’s task objectives. This poses a challenge: RNNs are susceptible to vanishing and exploding gradients, and naïve gradient descent-based strategies to solve long-horizon task objectives thus suffer from the same problems. To address this challenge, we introduce a novel gradient approximation algorithm based on the idea of dropout or gradient sampling. One of the main contributions is the notion ofcontroller network dropout, where we approximate the NN controller in several timesteps in the task horizon by the control input obtained using the controller in a previous training step. We show that our control synthesis methodology can be quite helpful for stochastic gradient descent to converge with less numerical issues, enabling scalable back-propagation over longer time horizons and trajectories over higher-dimensional state spaces. We demonstrate the efficacy of our approach on various motion planning applications requiring complex spatio-temporal and sequential tasks ranging over thousands of timesteps.more » « less
-
This study proposes a novel planning framework based on a model predictive control formulation that incorporates signal temporal logic (STL) specifications for task completion guarantees and robustness quantification. This marks the first-ever study to apply STL-guided trajectory optimization for bipedal locomotion push recovery, where the robot experiences unexpected disturbances. Existing recovery strategies often struggle with complex task logic reasoning and locomotion robustness evaluation, making them susceptible to failures due to inappropriate recovery strategies or insufficient robustness. To address this issue, the STL-guided framework generates optimal and safe recovery trajectories that simultaneously satisfy the task specification and maximize the locomotion robustness. Our framework outperforms a state-of-the-art locomotion controller in a high-fidelity dynamic simulation, especially in scenarios involving crossed-leg maneuvers. Furthermore, it demonstrates versatility in tasks such as locomotion on stepping stones, where the robot must select from a set of disjointed footholds to maneuver successfully.more » « less
-
There is a growing trend toward AI systems interacting with humans to revolutionize a range of application domains such as healthcare and transportation. However, unsafe human-machine interaction can lead to catastrophic failures. We propose a novel approach that predicts future states by accounting for the uncertainty of human interaction, monitors whether predictions satisfy or violate safety requirements, and adapts control actions based on the predictive monitoring results. Specifically, we develop a new quantitative predictive monitor based on Signal Temporal Logic with Uncertainty (STL-U) to compute a robustness degree interval, which indicates the extent to which a sequence of uncertain predictions satisfies or violates an STL-U requirement. We also develop a new loss function to guide the uncertainty calibration of Bayesian deep learning and a new adaptive control method, both of which leverage STL-U quantitative predictive monitoring results. We apply the proposed approach to two case studies: Type 1 Diabetes management and semi-autonomous driving. Experiments show that the proposed approach improves safety and effectiveness in both case studies.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3580490
