analiza aiqbench
CLASP bridges the data efficiency of task-parameterized imitation learning with the natural language grounding of pretrained vision-language models, enabling robots to compose novel behaviors from minimal demonstrations. By leveraging a modular architecture that generates skill schemas and interprets commands without fine-tuning, the system achieves high success rates in complex manipulation scenarios while actively requesting targeted data for capability gaps. This approach offers a practical pathway for deploying foundation models in robotics where extensive training datasets are unavailable.
CLASP: Language-Driven Robot Skill Selection and Composition using Task-Parameterized Learning
arXiv:2606.08169v1 Announce Type: cross Abstract: Enabling robots to understand and execute tasks from natural language commands while maintaining data efficiency remains challenging. Foundation models such as vision-language-action (VLA) and vision-language models (VLMs) provide intuitive interaction channels but require extensive data; task-parameterized imitation learning achieves data efficiency but lacks natural language grounding. This work bridges this gap through a modular architecture combining task-parameterized kernelized movement primitives (TP-KMPs) with pretrained VLMs. During learning, skills are acquired from 2 to 5 kinesthetic demonstrations, and the VLM generates skill schemas describing each skill's parameters and preconditions. During execution, the VLM interprets commands to select skills, reason about parameter bindings, and create novel behaviors through covariance-weighted composition. When no skill or composition suffices, the system identifies capability gaps and requests targeted demonstrations, all without fine-tuning. Validation on a 7-DoF manipulator shows success rates of 73.3%-100% in scenarios requiring skill selection, composition, and active learning.
Abstract:Enabling robots to understand and execute tasks from natural language commands while maintaining data efficiency remains challenging. Foundation models such as vision-language-action (VLA) and vision-language models (VLMs) provide intuitive interaction channels but require extensive data; task-parameterized imitation learning achieves data efficiency but lacks natural language grounding. This work bridges this gap through a modular architecture combining task-parameterized kernelized movement primitives (TP-KMPs) with pretrained VLMs. During learning, skills are acquired from 2 to 5 kinesthetic demonstrations, and the VLM generates skill schemas describing each skill's parameters and preconditions. During execution, the VLM interprets commands to select skills, reason about parameter bindings, and create novel behaviors through covariance-weighted composition. When no skill or composition suffices, the system identifies capability gaps and requests targeted demonstrations, all without fine-tuning. Validation on a 7-DoF manipulator shows success rates of 73.3%-100% in scenarios requiring skill selection, composition, and active learning.
Robotics (cs.RO); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
arXiv:2606.08169 [cs.RO]
(or arXiv:2606.08169v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.08169 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 · 250 cuvinte
Subiecte conexe
Skill-SLM: Agent Skill-driven Small Language Models for Reliable Robot Operation
arXiv · 9 oct. 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · 12 iun. 2026