analiza aiqbench
This research advances assistive autonomy by integrating neuro-symbolic reasoning with hierarchical planning to infer human goals before actions are fully observed. The approach combines neural predictive ranking with symbolic logic constraints, achieving significant improvements in trajectory validity and compositional generalization on a large multimodal benchmark. While the application involves human behavior analysis, the core innovation lies in the architectural fusion of neural networks and symbolic AI for structured goal inference.
Neuro-Symbolic Hierarchical Intention Anticipation in Human Behavior
arXiv:2609.17064v1 Announce Type: new Abstract: Assistive autonomous systems must anticipate human goals before an observed behavior is complete. This article formulates anticipation as goal inference from a partially observed multimodal episode together with structured prediction of the remaining behavior, rather than exact motor forecasting. A compact Hierarchical Planning Decoder (HPD) is attached to a frozen neuro-symbolic recognition encoder and predicts, at four ontological levels, the next actions, the remaining activities and low-level intentions, and the episode high-level intention(HLI). The decoder is trained with soft neuro-symbolic regularization combining transition-coherence and hierarchical continuity losses, and is decoded with hard reachability masks that enforce ontological validity at inference. On a compositional four-level benchmark of 15,002 multimodal episodes built over NTU RGB+D 120 features, three headline properties are observed together. The advantage over the strongest sequential baseline grows with the anticipation horizon, from +1.7 points at step 1 to +7.3 points at step 3 (top-5). Under compositional generalization, where one parent association per multi-parent low level intention is held out, this advantage widens to +4.9 points at step 1. At the episode level, 96.8% of anticipated trajectories satisfy the joint logic constraints, above the 88.1% strongest-baseline value and the 73.9% ground-truth floor; soft logic terms alone account for a 59.8 to 71.1% relative reduction of HLI-reachability violations, and the hard masks then eliminate them entirely. Neural generation supplies predictive ranking, symbolic constraints supply onto logical validity, and their combination yields coherent hierarchical anticipation while exposing remaining challenges in compositional goal generalization and unordered set prediction.
Abstract:Assistive autonomous systems must anticipate human goals before an observed behavior is complete. This article formulates anticipation as goal inference from a partially observed multimodal episode together with structured prediction of the remaining behavior, rather than exact motor forecasting. A compact Hierarchical Planning Decoder (HPD) is attached to a frozen neuro-symbolic recognition encoder and predicts, at four ontological levels, the next actions, the remaining activities and low-level intentions, and the episode high-level intention(HLI). The decoder is trained with soft neuro-symbolic regularization combining transition-coherence and hierarchical continuity losses, and is decoded with hard reachability masks that enforce ontological validity at inference. On a compositional four-level benchmark of 15,002 multimodal episodes built over NTU RGB+D 120 features, three headline properties are observed together. The advantage over the strongest sequential baseline grows with the anticipation horizon, from +1.7 points at step 1 to +7.3 points at step 3 (top-5). Under compositional generalization, where one parent association per multi-parent low level intention is held out, this advantage widens to +4.9 points at step 1. At the episode level, 96.8% of anticipated trajectories satisfy the joint logic constraints, above the 88.1% strongest-baseline value and the 73.9% ground-truth floor; soft logic terms alone account for a 59.8 to 71.1% relative reduction of HLI-reachability violations, and the hard masks then eliminate them entirely. Neural generation supplies predictive ranking, symbolic constraints supply onto logical validity, and their combination yields coherent hierarchical anticipation while exposing remaining challenges in compositional goal generalization and unordered set prediction.
Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
arXiv:2609.17064 [cs.AI]
(or arXiv:2609.17064v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.17064 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 281 cuvinte
Subiecte conexe
Neuro-Symbolic Graph Transformers for Hierarchical Intention Recognition from Multimodal Human Activity Sequences
arXiv · 15 oct. 2026
Uncertainty-Aware Intention Prediction for Human-to-Robot Assembly Teleoperation
arXiv · 9 iun. 2026
HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Models
arXiv · 17 sept. 2026
Towards embedded evaluations for scheming propensities
LessWrong · 8 oct. 2026