No Plan, Yet Human: A Reactive Robotics Model Predicts Human Planning Failures on a Clinical Task
Michael Migacev, Vito Mengers, Antonia K\"ongeter, Oliver Brock
Why It Matters
What makes this one worth your time
This research bridges robotics and cognitive science, offering insights into human planning processes that could inform both AI development and clinical assessments.
AICON effectively models human planning failures in clinical cognitive tasks without explicit planning mechanisms.
Summary
The paper presents AICON, a reactive gradient-descent model that predicts human planning failures in a cognitive task, demonstrating its ability to replicate human difficulty ordering without prior knowledge of human cognition.
Key contributions
- Demonstration of AICON's ability to predict human planning difficulties across various cognitive impairments.
- Comparison of AICON's performance against traditional planning models, revealing its advantages in specific patient groups.
- Extension of AICON's application from robotics to cognitive assessment, indicating its broader relevance.
Notable insights
- AICON's performance highlights a shift in human behavior towards reactive strategies under reduced planning capacity, mirroring the model's design.
- The model's failure modes align with specific cognitive impairments, suggesting a deeper connection between robotic frameworks and human cognitive processes.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2605.16514v1 Announce Type: cross Abstract: Understanding why some sequential planning problems are harder than others requires models that go beyond average performance. They should capture the specific pattern of which problems are hard, and ideally fail in the same way people do when planning capacity is reduced. We apply AICON, a reactive gradient-descent framework developed for robotic manipulation, to the Tower of London test, a cognitive test used to assess planning in Parkinson's disease, mild cognitive impairment, and stroke. Without any lookahead planning or knowledge of human cognition, AICON reproduces the fine-grained human difficulty ordering across 24 problems better than structural task parameters and generalizes to held-out problems in a leave-two-out evaluation. Crucially, AICON outperforms a planning baseline for groups with reduced planning capacity while the planning baseline better captures healthy controls. This dissociation was predicted by the original AICON paper, which noted that the model's failure modes resemble those of Parkinson's patients who struggle with goal hierarchies but not move counts. This suggests that as planning capacity is reduced, human behavior shifts toward the reactive mode AICON models. The finding extends a broader pattern: AICON, originally built for robotics, now captures aspects of biological behavior across perception, eye movements, and sequential planning, suggesting its core abstraction reflects something real about how biological systems are organized.