# The Constitutional Controller: Doubt-Calibrated Steering of Compliant Agents

arXiv: https://arxiv.org/abs/2507.15478 · HTML: https://mlsanity.com/paper/2507.15478/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 44 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 12 of 12)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Multi-shot ASP solving with clingo](https://mlsanity.com/paper/1705.09811/) (2017)
- [NeurASP: Embracing Neural Networks into Answer Set Programming](https://mlsanity.com/paper/2307.07700/) (2023)
- [Scalable Neural-Probabilistic Answer Set Programming](https://mlsanity.com/paper/2306.08397/) (2023)
- [Mission Design for Unmanned Aerial Vehicles using Hybrid Probabilistic Logic Programs](https://mlsanity.com/paper/2406.03454/) (2024)
- [Probabilistic Mission Design for Neuro-Symbolic Unmanned Aircraft Systems](https://mlsanity.com/paper/2501.01439/) (2024)
- [Towards Probabilistic Clearance, Explanation and Optimization](https://mlsanity.com/paper/2406.15088/) (2024)
- [The Constitutional Filter: Bayesian Estimation of Compliant Agents](https://mlsanity.com/paper/2412.18347/) (2024)
- [StaR Maps: Unveiling Uncertainty in Geospatial Relations](https://mlsanity.com/paper/2412.18356/) (2024)
- [Scalar Field Mapping with Adaptive High-Intensity Region Avoidance](https://mlsanity.com/paper/2407.13543/) (2024)

## Built on by (most cited first, 1 of 1)

- [Right in Time: Reactive Reasoning in Regulated Traffic Spaces](https://mlsanity.com/paper/2603.03977/) (2026)

## Abstract (arXiv)

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.