The field of robotics is moving towards the development of more advanced and versatile robotic systems, with a focus on improving design, control, and interaction with the environment. Recent research has explored the use of novel materials, mechanisms, and control strategies to enhance robotic capabilities, such as compliant and adaptive robots, humanoid robots, and soft robotic actuators. Noteworthy papers include 'Developing a Mono-Actuated Compliant GeoGami Robot', which presents a new soft-rigid robotic platform, and 'Towards Versatile Humanoid Table Tennis', which proposes a reinforcement learning framework for humanoid table tennis. Other notable works include 'WAVE: Worm Gear-based Adaptive Variable Elasticity' and 'OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction'.
Advancements in Robotic Design and Control
Sources
Developing a Mono-Actuated Compliant GeoGami Robot
Towards Versatile Humanoid Table Tennis: Unified Reinforcement Learning with Prediction Augmentation
WAVE: Worm Gear-based Adaptive Variable Elasticity for Decoupling Actuators from External Forces
One-DoF Robotic Design of Overconstrained Limbs with Energy-Efficient, Self-Collision-Free Motion
Multi-stage robust nonlinear model predictive control of a lower-limb exoskeleton robot
Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint
Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning and Control-Informed Steering
CoTaP: Compliant Task Pipeline and Reinforcement Learning of Its Controller with Compliance Modulation
MoReFlow: Motion Retargeting Learning through Unsupervised Flow Matching
Physics-Informed Learning for Human Whole-Body Kinematics Prediction via Sparse IMUs
State Estimation for Compliant and Morphologically Adaptive Robots
Evolutionary Continuous Adaptive RL-Powered Co-Design for Humanoid Chin-Up Performance
OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction
A Novel Robust Control Method Combining DNN-Based NMPC Approximation and PI Control: Application to Exoskeleton Squat Movements
Learning Human Reaching Optimality Principles from Minimal Observation Inverse Reinforcement Learning
Modeling and Mixed-Integer Nonlinear MPC of Positive-Negative Pressure Pneumatic Systems
Formation Control via Rotation Symmetry Constraints
A Stochastic Framework for Continuous-Time State Estimation of Continuum Robots
Pose Estimation of a Thruster-Driven Bioinspired Multi-Link Robot
PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomization
Like Playing a Video Game: Spatial-Temporal Optimization of Foot Trajectories for Controlled Football Kicking in Bipedal Robots
SPARC: Spine with Prismatic and Revolute Compliance for Quadruped Robot
Stand Up, NAO! Increasing the Reliability of Stand-Up Motions Through Error Compensation in Position Control
Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking