This work separates behavior learning from temporal composition, allowing demonstrated behaviors to be reused in longer, previously unseen temporal compositions without retraining, and demonstrates reliable execution of complex temporal instructions and additional safety constraints, with substantial improvements over...
Moritz Zoellner, Anastasios Manganaris, A. H. Qureshi et al.· 1 citation
Motion planning on arbitrary Riemannian manifolds is an important and difficult problem that frustrates typical planning methods for Euclidean spaces. In particular, motion planning methods that approximate optimal time-to-go functions with neural networks, e.g., Neural Time Fields (NTFields), cannot be directly applie...
Anastasios Manganaris, R. Banerjee, Gokul Prabhakaran et al.· 0 citations
This paper introduces hint, a method for guiding short-horizon policies toward satisfying complex LTL specifications at inference time using hierarchical world models, and shows that hint$^2$ can handle complex instructions on a real UR5e manipulator.
Moritz Zoellner, Anastasios Manganaris, A. H. Qureshi et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.