analiza aiqbench
This research introduces a fully differentiable framework that unifies visual perception and logical task planning within a single computational graph, effectively bridging the gap between continuous uncertainty and discrete symbolic rules. By allowing gradients from planning objectives to refine perceptual representations in real-time, the method achieves superior success rates on robotic benchmarks like Blocksworld while reducing computational overhead. This advancement represents a significant step toward robust embodied AI systems capable of handling complex, uncertain environments with end-to-end optimization.
A Fully Differentiable Neuro-Soft-Symbolic Framework for Perceptual Task Planning
arXiv:2609.21221v1 Announce Type: new Abstract: Perceptual planning tasks require two key capabilities: accurately perceiving uncertain scenes and planning valid action sequences following logical rules. Conventional methods convert perception into discrete symbolic facts and then plan, discarding perceptual uncertainty and severing task-level feedback to perception. We introduce a generic, fully differentiable neuro-soft-symbolic framework that connects visual perception and task planning within a single computational graph. The framework maintains a continuous soft symbolic state, lifts domain rules into a differentiable soft-$T_P$ transition operator, and optimizes action logits over a short planning horizon. Gradients from the planning objective can also update the perception parameters, allowing task-relevant perceptual representations to be refined during planning. On Blocksworld, our method solves 40/40 LatPlan-40 tasks and 596/600 PlanBench-600 tasks, compared with 33/40 for LatPlan and 587/600 for the reasoning-model baseline, while requiring substantially less computation and time. In the perceptual-uncertainty ablation, our method improves the success rate from 59\% with frozen perception to 83\%. We further conduct task-and-motion simulations on Blocksworld scenes, providing an execution-level validation of the compatibility between decoded task plans and downstream robotic motion execution.
Abstract:Perceptual planning tasks require two key capabilities: accurately perceiving uncertain scenes and planning valid action sequences following logical rules. Conventional methods convert perception into discrete symbolic facts and then plan, discarding perceptual uncertainty and severing task-level feedback to perception. We introduce a generic, fully differentiable neuro-soft-symbolic framework that connects visual perception and task planning within a single computational graph. The framework maintains a continuous soft symbolic state, lifts domain rules into a differentiable soft-$T_P$ transition operator, and optimizes action logits over a short planning horizon. Gradients from the planning objective can also update the perception parameters, allowing task-relevant perceptual representations to be refined during planning. On Blocksworld, our method solves 40/40 LatPlan-40 tasks and 596/600 PlanBench-600 tasks, compared with 33/40 for LatPlan and 587/600 for the reasoning-model baseline, while requiring substantially less computation and time. In the perceptual-uncertainty ablation, our method improves the success rate from 59\% with frozen perception to 83\%. We further conduct task-and-motion simulations on Blocksworld scenes, providing an execution-level validation of the compatibility between decoded task plans and downstream robotic motion execution.
Artificial Intelligence (cs.AI); Robotics (cs.RO)
arXiv:2609.21221 [cs.AI]
(or arXiv:2609.21221v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.21221 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 272 cuvinte
Subiecte conexe
SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data
arXiv · 23 iul. 2026
DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
arXiv · 4 aug. 2026
Neuro-Symbolic Predicate Learning for Semantic Safe Robot Control
arXiv · 1 oct. 2026
Soft Symbol Grounding for Prototypical Concepts
arXiv · 14 sept. 2026