The Constitutional Controller: Doubt-Calibrated Steering of Compliant Agents

• URL: http://arxiv.org/abs/2507.15478v1
• Date: Mon, 21 Jul 2025 10:33:31 GMT
• Title: The Constitutional Controller: Doubt-Calibrated Steering of Compliant Agents
• Authors: Simon Kohaut, Felix Divo, Navid Hamid, Benedict Flade, Julian Eggert, Devendra Singh Dhami, Kristian Kersting,
• Abstract summary: We show how neuro-symbolic systems integrate probabilistic, symbolic white-box reasoning models with deep learning methods.<n>This enables the simultaneous consideration of explicit rules and neural models trained on noisy data.<n>In a real-world aerial mobility study, we demonstrate CoCo's advantages for intelligent autonomous systems to learn appropriate doubts.
• Score: 18.680037980430797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ensuring reliable and rule-compliant behavior of autonomous agents in uncertain environments remains a fundamental challenge in modern robotics. Our work shows how neuro-symbolic systems, which integrate probabilistic, symbolic white-box reasoning models with deep learning methods, offer a powerful solution to this challenge. This enables the simultaneous consideration of explicit rules and neural models trained on noisy data, combining the strength of structured reasoning with flexible representations. To this end, we introduce the Constitutional Controller (CoCo), a novel framework designed to enhance the safety and reliability of agents by reasoning over deep probabilistic logic programs representing constraints such as those found in shared traffic spaces. Furthermore, we propose the concept of self-doubt, implemented as a probability density conditioned on doubt features such as travel velocity, employed sensors, or health factors. In a real-world aerial mobility study, we demonstrate CoCo's advantages for intelligent autonomous systems to learn appropriate doubts and navigate complex and uncertain environments safely and compliantly.

Related papers

• Formal Control for Uncertain Systems via Contract-Based Probabilistic Surrogates (Extended Version) [1.474723404975345]
  We provide an abstraction-based technique that scales effectively to higher dimensions while addressing complex nonlinear agent-environment interactions.<n>Our approach trades scalability for conservatism favorably, as demonstrated on a complex high-dimensional vehicle intersection.
  arXiv  Detail & Related papers  (2025-06-20T13:00:50Z)
• Towards Responsible AI: Advances in Safety, Fairness, and Accountability of Autonomous Systems [0.0]
  This thesis advances knowledge in the safety, fairness, transparency, and accountability of AI systems.<n>We extend classical deterministic shielding techniques to become resilient against delayed observations.<n>We introduce fairness shields, a novel post-processing approach to enforce group fairness in sequential decision-making settings.
  arXiv  Detail & Related papers  (2025-06-11T21:30:02Z)
• Towards provable probabilistic safety for scalable embodied AI systems [79.31011047593492]
  Embodied AI systems are increasingly prevalent across various applications.<n> Ensuring their safety in complex operating environments remains a major challenge.<n>We introduce provable probabilistic safety, which aims to ensure that the residual risk of large-scale deployment remains below a predefined threshold.
  arXiv  Detail & Related papers  (2025-06-05T15:46:25Z)
• Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation [55.02966123945644]
  We propose a hierarchical control framework leveraging neural network verification techniques to design control barrier functions (CBFs) and policy correction mechanisms.<n>Our approach relies on probabilistic enumeration to identify unsafe regions of operation, which are then used to construct a safe CBF-based control layer.<n>These experiments demonstrate the ability of the proposed solution to correct unsafe actions while preserving efficient navigation behavior.
  arXiv  Detail & Related papers  (2025-04-30T13:47:25Z)
• Modular Framework for Uncertainty Prediction in Autonomous Vehicle Motion Forecasting within Complex Traffic Scenarios [6.6603214802161546]
  Our framework employs a flexible, end-to-end differentiable probabilistic encoder-decoder architecture.<n>Key contributions include a probabilistic heatmap predictor that generates context-aware occupancy grids for dynamic forecasting.<n>We benchmark it against an end-to-end baseline, demonstrating faster convergence, improved stability, and flexibility.
  arXiv  Detail & Related papers  (2025-01-27T20:21:18Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions [60.26921219698514]
  We introduce a model-uncertainty-aware reformulation of CBF-based safety-critical controllers. We then present the pointwise feasibility conditions of the resulting safety controller. We use these conditions to devise an event-triggered online data collection strategy.
  arXiv  Detail & Related papers  (2022-08-23T05:02:09Z)
• CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning [68.74447489372037]
  We present a high-fidelity simulation environment that is designed for developing algorithms for causal discovery and counterfactual reasoning. A core component of our work is to introduce textitagency, such that it is simple to define and create complex scenarios. We perform experiments with three state-of-the-art methods to create baselines and highlight the affordances of this environment.
  arXiv  Detail & Related papers  (2021-06-25T00:21:41Z)
• Probabilistic robust linear quadratic regulators with Gaussian processes [73.0364959221845]
  Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design. We present a novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin.
  arXiv  Detail & Related papers  (2021-05-17T08:36:18Z)
• Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance [110.63037190641414]
  We propose to learn congestion patterns explicitly and devise a novel "Sense--Learn--Reason--Predict" framework. By decomposing the learning phases into two stages, a "student" can learn contextual cues from a "teacher" while generating collision-free trajectories. In experiments, we demonstrate that the proposed model is able to generate collision-free trajectory predictions in a synthetic dataset.
  arXiv  Detail & Related papers  (2021-03-26T02:42:33Z)
• Online Mapping and Motion Planning under Uncertainty for Safe Navigation in Unknown Environments [3.2296078260106174]
  This manuscript proposes an uncertainty-based framework for mapping and planning feasible motions online with probabilistic safety-guarantees. The proposed approach deals with the motion, probabilistic safety, and online computation constraints by: (i) mapping the surroundings to build an uncertainty-aware representation of the environment, and (ii) iteratively (re)planning to goal that are kinodynamically feasible and probabilistically safe through a multi-layered sampling-based planner in the belief space.
  arXiv  Detail & Related papers  (2020-04-26T08:53:37Z)
• A Structured Approach to Trustworthy Autonomous/Cognitive Systems [4.56877715768796]
  There is no generally accepted approach to ensure trustworthiness. This paper presents a framework to exactly fill this gap. It proposes a reference lifecycle as a structured approach that is based on current safety standards.
  arXiv  Detail & Related papers  (2020-02-19T14:36:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.