Rainbow Deep Q-Learning with Kinematics-Aware Design for Cooperative Delta and 3-RRS Parallel Robot Insertion

This paper presents a kinematics-aware deep reinforcement learning framework based on Rainbow Deep Q-Networks (DQN) for cooperative peg-in-hole manipulation by a Delta parallel robot and a 3-RRS (Revolute--Revolute--Spherical) parallel manipulator. A key contribution is the integration of a geometric design-optimization stage that precedes learning: the 3-RRS geometry is tuned to maximize the singularity-free workspace and improve conditioning, which in turn enlarges the safe region in which the reinforcement learning policy can explore. Together the two manipulators expose a 6~degree-of-freedom (DoF) controllable subspace (three Delta translations, two 3-RRS rotations, and one 3-RRS vertical translation); the peg-in-hole task is invariant to rotation about the peg axis, so the task-relevant manifold is five dimensional. The cooperative insertion problem is cast as a Markov Decision Process with a 12-dimensional state vector and a discrete action set containing $6 \times 2 = 12$ incremental commands (one positive and one negative per controlled DoF). A shaped reward combines dense proximity guidance, penalties for kinematic and workspace violations, and sparse bonuses for successful insertions. The Rainbow DQN -- integrating double Q-learning, dueling architecture, prioritized replay, multi-step returns, noisy linear layers for exploration, and a distributional value head -- is trained with a two-stage curriculum. The co-designed framework is validated in a high-fidelity kinematic simulator, where it achieves stable policy convergence, reliable insertions, and reduced constraint violations compared against a vanilla DQN agent and a classical sampling-based planner.

Unveiling the Complete Variant of Spherical Robots

This study presents a systematic enumeration of spherical ($SO(3)$) type parallel robots' variants using an analytical velocity-level approach. These robots are known for their ability to perform arbitrary rotations around a fixed point, making them suitable for numerous applications. Despite their architectural diversity, existing research has predominantly approached them on a case-by-case basis. This approach hinders the exploration of all possible variants, thereby limiting the benefits derived from architectural diversity. By employing a generalized analytical approach through the reciprocal screw method, we systematically explore all the kinematic conditions for limbs yielding $SO(3)$ motion.Consequently, all 73 possible types of non-redundant limbs suitable for generating the target $SO(3)$ motion are identified. The approach involves performing an in-depth algebraic motion-constraint analysis and identifying common characteristics among different variants. This leads us to systematically explore all 73 symmetric and 5256 asymmetric variants, which in turn become a total of 5329, each potentially having different workspace capability, stiffness performance, and dynamics. Hence, having all these variants can facilitate the innovation of novel spherical robots and help us easily find the best and optimal ones for our specific applications.