New robotics and physical-AI papers, with what each one means for the industry.
Generalist robot policies are trained with imitation learning and are bounded by the quality and coverage of their demonstrations. Reinforcement learning can improve and extend them, either by fine-tuning the policy weights or by training a small module to steer the input noise of a frozen generative policy.
This preprint presents AdaTempo, a self-supervised method that speeds up visuomotor imitation policies by extracting shared phase-relative tempo patterns from demonstrations and resampling trajectories before training. It achieves up to a 3.57x speedup over demonstrations, and in real-robot tests raises aggregate success from 58.3% with ACT to 77.8% while completing tasks 2.02x faster. The approach matters because it embeds faster execution directly into standard policies such as ACT or Diffusion Policy without runtime retiming or extra speed-selection modules.
This preprint introduces VISTA, a diffusion-policy architecture that fuses wrist camera and tactile images into a rotation-equivariant spherical representation for contact-rich manipulation. In simulation with 50 demonstrations per task it reaches 80.9% mean success, outperforming an equivariant tactile baseline by 15.9 points, and on three real-robot tasks it succeeds in 7.33/10 trials versus 1.33/10 for that baseline. The design could reduce the demonstration data needed for tight-insertion and surface-contact tasks by encoding workspace rotation symmetry into visuotactile perception.
The authors present Sub-ID, a submovement decomposition method for human hand trajectories that uses a spatiotemporal kernel correlation as an identifiability criterion, and it is described as a preprint. On synthetic tests with 3, 8, and 15 overlapping primitives it recovers ground-truth parameter distributions where baselines degrade or fail, holding position error to 0.012 m at K=15 and keeping critical primitive overlaps to about 3%. This gives robotics and motor-control researchers a practical way to extract physiologically grounded motion primitives from long, three-dimensional movements.
Robot AI models plan a short burst of movements at a time, and how many of those moves the robot carries out before it looks again is usually fixed by hand. This preprint from Tsinghua University, BAAI and partners adds a plug-in that picks that number while the robot works, raising success rates of existing Physical Intelligence and NVIDIA models in simulation and on a real two-arm robot without retraining them.
Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators are not always optimal. We propose Blended DAgger (BlenDAgger), an approach for collecting data to train imitation learning policies by using shared control to blend the policy's and demonstrator's actions during interventions.
While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to robot manipulation learning predominantly represent actions as target positions or poses. Even methods that incorporate force sensing either use it solely as an observation or, when predicting forces as part of the output, rely on a hybrid force controller.
Co-training a VLA on heterogeneous data (multi-robot, web, high-level subtask labels) lets a mobile manipulator clean unseen homes end-to-end.
Papers come from arXiv robotics feeds. Where our summary is not written yet, you see the opening lines of the abstract.