Publication
The Constitutional Controller: Doubt-Calibrated Steering of Compliant Agents
Simon Kohaut; Felix Divo; Navid Hamid; Benedict Flade; Julian Eggert; Devendra Singh Dhami; Kristian Kersting
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2507.15478, Pages 1-11, Computing Research Repository, 2025.
Abstract
Ensuring reliable and rule-compliant behavior of
autonomous agents in uncertain environments remains a fun-
damental 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 strengths 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.