Psi R1

Overview

Psi R1 employs a dual-system brain architecture to enable human-like dexterous control and long-horizon autonomous reasoning, delivering precision, generalization, and interactive capability across real-world applications. It supports CoAT task chains exceeding 30 minutes, millimeter-level precision, and 16-DOF exoskeleton teleoperation.

Key features

• ▸Dual-system brain architecture for long-horizon autonomous reasoning and operation closed-loop
• ▸Supports CoAT task chains exceeding 30 minutes
• ▸Fast/slow brain collaboration with integrated perception-reasoning-execution
• ▸Reinforcement learning-driven self-reflection and strategy optimization
• ▸Humanoid dexterous manipulation with millimeter-level precision
• ▸Full-hand tactile + force control system supporting blind grasping and precise force output
• ▸16-DOF exoskeleton teleoperation highly replicating human hand movements
• ▸Three-way interaction: human-robot, machine-machine, machine-environment
• ▸Modular whole-machine solution supporting large-scale low-cost deployment