ROBOTNESS
Research

Papers

New robotics and physical-AI papers, with what each one means for the industry.

5 papers
TopicAllManipulation · 18VLA · 15Navigation · 14Perception · 9Robotics · 9Learning · 6Humanoid · 5Safety · 3Simulation · 3Aerial Manipulation · 1Co-speech Humanoid · 1Distributed Manipulation · 1Floorplan SLAM · 1Grounding · 1Humanoid control · 1Locomotion · 1Memory-centric VLA · 1Model-based RL · 1Multi-UAV State Estimation · 1Policy · 1Real-time VLA · 1Safe RL-MPC · 1Safe VLA · 1Soft Pneumatic Actuators · 1Tactile · 1Terrain traversability · 1Text-to-3D Policy · 1Tool Co-Design · 1UAV Navigation · 1UAV traffic monitoring · 1Visual Grounding · 1World models · 1World-action model · 1
LevelAnyBeginnerIntermediateExpert
Filtered by technology world-model · clear
arXiv
Model-based RLExpert

Beyond Policy Alignment: Closing the Planning-Learning Loop for Robot Control with Learned World Models

Kowndinya Boyalakuntla, Yuhan Liu, Abdeslam Boularias

This preprint extends policy-constrained TD-MPC into PL-MPC by changing critic training targets, MPPI terminal values, and actor distillation without altering the world model or planner. On HumanoidBench, it lifts total average return from 98±18 to 387±255 on balance-hard and from 199±13 to 466±200 on hurdle; in zero-shot sim-to-real wrench–nut alignment on a KUKA IIWA14 it achieves 74.2% vs 61.3% success on the training object size. The result matters because it shows targeted interactions in the planning–learning loop can improve hard robot control tasks beyond the usual planner–policy alignment.

World Models
Read the full paper (PDF)
arXiv
ManipulationIntermediate

RoboCoach: World Models as Active Coaches for Compositional Robot Skills

Jiajun Liu, Yifan Chen, Yichao Liu, Jiayi Zhang, Ruoqu Chen, Shaoxuan Xie, Guocai Yao, Mengdi Xu, Sen Cui, Changshui Zhang

This preprint introduces RoboCoach, a world-model-guided coaching loop that decides which subtask demonstrations to collect and which reusable skill expert adapters to update. On real robots, 150 added subtask demonstrations lift complete-task success from 13.3% to 75.0% on Franka and from 40.0% to 83.8% on AgileX, and coached skills transfer to four unseen compositions where a baseline scores 0%. The work matters because it shows world models can direct scarce real-world supervision toward the specific reusable skills that fail, rather than requiring expensive end-to-end data.

World Models
Read the full paper (PDF)
arXiv
LearningExpert

Anisotropic Representations Improve Planning in JEPA World Models

Mingu Kang, Yoori Oh, Sookyung Kim, Joonseok Lee

Latent world models learn action-conditioned dynamics in representation space and often score candidate actions by Euclidean distance to a goal representation. Joint training typically regularizes the representation to prevent collapse, but the resulting representation geometry also determines how terminal errors are weighted during planning.

World Models
Read the full paper (PDF)

Topic pages

Manipulation · 18Navigation · 14VLA · 14Perception · 9General robotics · 9Robot learning · 6Humanoid · 5Safety · 3Simulation · 3

Papers come from arXiv robotics feeds. Where our summary is not written yet, you see the opening lines of the abstract.