Robotic Manipulation Comparison Hub

Reference Surfaces

Top Papers

• Characterization, Analytical Planning, and Hybrid Force Control for the Inspire RH56DFX Hand(8.0)

  Transform the Inspire RH56DFX hand into a reliable research tool for dexterous manipulation with enhanced control and planning capabilities.

• NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning(8.0)

  NovaPlan enables robots to perform zero-shot, long-horizon manipulations using video language planning, achieving state-of-the-art results without prior demonstrations.

• TiPToP: A Modular Open-Vocabulary Planning System for Robotic Manipulation(8.0)

  TiPToP is a modular open-vocabulary planning system that enables robotic manipulation from images and natural language instructions.

• FG-CLTP: Fine-Grained Contrastive Language Tactile Pretraining for Robotic Manipulation(8.0)

  FG-CLTP enhances robotic manipulation by integrating fine-grained tactile sensing with vision-language-action models.

• DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation(8.0)

  DexHiL is a human-in-the-loop framework that enhances dexterous manipulation in robotic systems through coordinated interventions and adaptive learning.

• Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulation(7.0)

  Ada3Drift enhances robotic manipulation by enabling high-fidelity single-step action generation through adaptive training-time drifting.

• Concurrent Prehensile and Nonprehensile Manipulation: A Practical Approach to Multi-Stage Dexterous Tasks(7.0)

  DexMulti enables efficient multi-stage dexterous manipulation in robotics by leveraging object-centric skills.

• Vision-Based Hand Shadowing for Robotic Manipulation via Inverse Kinematics(7.0)

  A hand-shadowing pipeline for robotic manipulation that translates human hand movements into robot commands using inverse kinematics.

• Stein Variational Ergodic Surface Coverage with SE(3) Constraints(7.0)

  A novel SE(3) Stein Variational Gradient Descent approach for optimizing robotic surface coverage trajectories.

• NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models(7.0)

  NS-VLA is a Neuro-Symbolic framework that enhances robotic manipulation through efficient learning and action sequencing.