Accurate system modeling is crucial for safe, effective control, as misidentification can lead to accumulated errors, especially under partial observability. We address this problem by formulating informative input design and model identification adaptive control (MIAC) as belief space planning problems, modeled as partially observable Markov decision processes with belief-dependent rewards (ρ-POMDPs). We treat system parameters as hidden state variables that must be localized while simultaneously controlling the system. We solve this problem with an adapted belief-space iterative Linear Quadratic Regulator (BiLQR). We demonstrate it on fully and partially observable tasks for cart-pole and steady aircraft flight domains. Our method outperforms baselines such as regression, filtering, and local optimal control methods, even under instantaneous disturbances to system parameters.

Distributionally robust control is a well-studied framework for optimal decision making under uncertainty, with the objective of minimizing an expected cost function over control actions, assuming the most adverse probability distribution from an ambiguity set. We consider an interpretable and expressive class of ambiguity sets defined by constraints on the expected value of functions of one-dimensional linear projections of the uncertain parameters. Prior work has shown that, under conditions, problems in this class can be reformulated as finite convex problems. In this work, we propose two iterative methods that can be used to approximately solve problems of this class in the general case. The first is an approximate algorithm based on best-response dynamics. The second is an approximate method that first reformulates the problem as a semi-infinite program and then solves a relaxation. We apply our methods to portfolio construction and trajectory planning scenarios.

Lagrangian-guided Monte Carlo tree search with global dual ascent has been applied to solve large constrained partially observable Markov decision processes (CPOMDPs) online. In this work, we demonstrate that these global dual parameters can lead to myopic action selection during exploration, ultimately leading to suboptimal decision making. To address this, we introduce history-dependent dual variables that guide local action selection and are optimized with recursive dual ascent. We empirically compare the performance of our approach on a motivating toy example and two large CPOMDPs, demonstrating improved exploration, and ultimately, safer outcomes.

Optimal plans in Constrained Partially Observable Markov Decision Processes (CPOMDPs) maximize reward objectives while satisfying hard cost constraints, generalizing safe planning under state and transition uncertainty. Unfortunately, online CPOMDP planning is extremely difficult in large or continuous problem domains. In many large robotic domains, hierarchical decomposition can simplify planning by using tools for low-level control given high-level action primitives (options). We introduce Constrained Options Belief Tree Search (COBeTS) to leverage this hierarchy and scale online search-based CPOMDP planning to large robotic problems. We show that if primitive option controllers are defined to satisfy assigned constraint budgets, then COBeTS will satisfy constraints anytime. Otherwise, COBeTS will guide the search towards a safe sequence of option primitives, and hierarchical monitoring can be used to achieve runtime safety. We demonstrate COBeTS in several safety-critical, constrained partially observable robotic domains, showing that it can plan successfully in continuous CPOMDPs while non-hierarchical baselines cannot.

Designing a safe and human-like decision-making system for an autonomous vehicle is a challenging task. Generative imitation learning is one possible approach for automating policy-building by leveraging both real-world and simulated decisions. Previous work that applies generative imitation learning to autonomous driving policies focuses on learning a low-level controller for simple settings. However, to scale to complex settings, many autonomous driving systems combine fixed, safe, optimization-based low-level controllers with high-level decision-making logic that selects the appropriate task and associated controller. In this paper, we attempt to bridge this gap in complexity by employing Safety-Aware Hierarchical Adversarial Imitation Learning (SHAIL), a method for learning a high-level policy that selects from a set of low-level controller instances in a way that imitates low-level driving data on-policy. We introduce an urban roundabout simulator that controls non-ego vehicles using real data from the Interaction dataset. We then demonstrate empirically that even with simple controller options, our approach can produce better behavior than previous approaches in driver imitation that have difficulty scaling to complex environments. Our implementation is available at https://github.com/sisl/InteractionImitation.