A 12B-parameter VLM learns to synthesize executable Behavior Tree policies from multimodal inputs via synthetic neuro-symbolic supervision, achieving zero-shot real-world transfer on robotic manipulators.
Mujoco: A physics engine for model-based control
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
fields
cs.RO 6years
2026 6representative citing papers
An intent-driven Real2Sim framework uses VLMs for semantic task decomposition to identify missing physical parameters and generates reactive behavior trees to acquire them via contact-rich robotic interactions on a Franka Panda arm.
Spectral Movement Primitives encode demonstrations as low-frequency Fourier coefficients and enforce joint limits by phase regulation without changing the represented end-effector path.
A two-stage CMA-ES co-design of a planar five-bar monoped, including motor/gearbox maps, yields ~30.4% farther jumps and ~11.5% less mechanical energy in simulation.
A PPO policy trained in Isaac Sim with domain randomization balances and steers a bicycle in sim (99.9% success) and transfers to real hardware.
A neuromorphic spiking ring attractor maintains stable multi-second representations of robot joint angles with reduced drift near limits and a near-linear velocity-to-bump-speed relationship.
citing papers explorer
-
Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision
A 12B-parameter VLM learns to synthesize executable Behavior Tree policies from multimodal inputs via synthetic neuro-symbolic supervision, achieving zero-shot real-world transfer on robotic manipulators.
-
Real2Sim via Active Perception with Behavior Trees Automatically Generated by VLMs
An intent-driven Real2Sim framework uses VLMs for semantic task decomposition to identify missing physical parameters and generates reactive behavior trees to acquire them via contact-rich robotic interactions on a Franka Panda arm.
-
SPECTRA: Context-Conditioned Spectral Movement Primitives for Robot Skill Generalization
Spectral Movement Primitives encode demonstrations as low-frequency Fourier coefficients and enforce joint limits by phase regulation without changing the represented end-effector path.
-
A Co-Design Framework for High-Performance Jumping of a Five-Bar Monoped with Actuator Optimization
A two-stage CMA-ES co-design of a planar five-bar monoped, including motor/gearbox maps, yields ~30.4% farther jumps and ~11.5% less mechanical energy in simulation.
-
CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control
A PPO policy trained in Isaac Sim with domain randomization balances and steers a bicycle in sim (99.9% success) and transfers to real hardware.
-
Neuromorphic Spiking Ring Attractor for Proprioceptive Joint-State Estimation
A neuromorphic spiking ring attractor maintains stable multi-second representations of robot joint angles with reduced drift near limits and a near-linear velocity-to-bump-speed relationship.