BLOG
Tsinghua AIR and Z-Trans AI present Zetta ζ, a closed-loop embodied harness that improves a frozen VLA policy without a single gradient update. Instead of fine-tuning, it evolves the execution harness around the policy: code-based runtime critics watch every action, recovery skills take over on deviation, and a validation gate admits only skills that generalize. The frozen baseline scores 31.0% on LIBERO-Pro; the same policy under Zetta ζ reaches 92.5% (+56.3 absolute points), with a +20-point gain to 93.6% across 18 RoboCasa tasks. Z-Infra scales valid rollout throughput 20.6× and speeds inference 11.1×. Skills transfer zero-shot, and clear robotic "aha moments" emerge.
glass-LIO is an open-source scan-to-map LiDAR-inertial odometry for the Livox MID-360, described by its author as “written to be read”: each of its six pipeline stages has a deep-dive write-up, the manifold Gauss-Newton solver is under 200 lines of Eigen with no Ceres/GTSAM, and every bug that produces plausible output is documented — including the full failure post-mortem of tight coupling diverging on real data. It runs real time at 10 Hz on the test bag with zero dropped scans and steady RMSE around 0.13 m.
Perplexity details Portable Computer, a local-first agent whose model, harness, conversation and trajectory live on-device by default, with web search, connectors and cloud advisor escalation only on user-approved demand. A lean local harness (on-demand skills, CLI connectors, self-verification, sandboxed execution) is co-designed around Qwen 3.8 27B, then post-trained into PPLX 27B. On the 53-task Local Knowledge Work Bench, Computer scores 82.6% vs Hermes 74.0% and Pi 77.6%, rising to 85.4% with PPLX 27B; it also leads BrowseComp (66.7%) and ParseBench-100 (65.1%) with the least time and tokens, while advisor escalation recovers ~3/5 of the Terminal Bench 2.1 frontier gap at ~2/3 of frontier cost.
NVIDIA COMPASS framework enables cross-embodiment navigation via residual RL and skill synthesis. A coding agent automates environment validation, scene preparation, smoke testing, residual specialist training, and checkpoint evaluation with human approval gates. Uses Spot quadruped as reference across built-in warehouse, SAGE-10K, and NuRec captured environments.
Dyna says Din Tai Fung will scale its robots after crossing the customer ROI threshold. Dyna-2 raises napkin folding from 35 to 95 per hour with quality improving from 75% to 93%, reaching 1,590 table-ready napkins daily. The essay details the production stack: reliable episode capture, automatic SOP labeling, failure drill-downs, hardware degradation prediction, and a deployment flywheel that can reach ROI in three days.
MHS uses standardized drivers, read/write primitives, natural-language machine descriptions, and MCP/CLI/API control to connect heterogeneous lab and manufacturing equipment to AI agents. The preview includes AWS, Doosan, Universal Robots, Tecan, QIAGEN and others, while emphasizing expert oversight for physical reasoning and safety.
Meta Reality Labs Research open-sourced Project SuperDex, a unified dexterous-manipulation simulation platform built on a custom contact-first physics engine with soft-body/rod/non-convex contact support, VR teleoperation for synthetic data, and a Gymnasium-style RL stack that achieved zero-shot sim2real shape sorting.
How should robot joint modules actually be selected? Drawing on 200+ joint-module/reducer entries in the RobotWorld knowledge base, product research on leading vendors (Harmonic Drive, Nabtesco, Leaderdrive, Laifual, Leadshine, EYOBOT, ZeroErr, JIECANG, CubeMars, ENCOS), and item-by-item verification of the supply chains behind Tesla, Unitree, UBTECH, AgiBot and Fourier, this guide systematically compares harmonic, planetary, RV, cycloidal and quasi-direct-drive (QDD) transmission routes on performance and cost, provides a torque-tier product cheat-sheet (0.5-200 N·m) and full configuration recipes by robot weight class (small <=25kg / mid 30-55kg / large 60-100kg), plus a practical pitfall-avoidance playbook.
Isaac 0.5 is Perceptron's open-source embodied foundation model with 36B sparse parameters: it reads images, video, language, robot state and previous actions to answer video questions, point and track objects, report task progress, and generate robot actions. The team establishes a scaling law trading video for teleop: scaling general video from 1,000 to 1M hours cuts the teleoperation needed for action loss 2.50 from ~5,900 hours to 28 (210x). Trained on 35+ robot systems, 100K hours of robot experience, 1M hours of video and 3T multimodal tokens, it introduces semantic world modeling (predicting future percepts), the mHarmony typed multimodal interface, and Null Experts for dynamic compute — leading all five perception task families at 8.5x lower inference cost. Weights, training code and LeRobot inference code are fully released.
Skild AI's flagship robotic foundation model S1 is built from the ground up as an in-context learner: show it a video demonstration of a task — even an unseen 10-minute long-horizon one — and it executes with no fine-tuning. On unseen tasks, one demonstration ≈ 380 post-training examples; at 100k pre-training hours S1 reaches 66% success vs 9% for language-prompted VLAs.
自研机器人结构件该用什么材料？基于三份独立工程指南的交叉核验，从结构强度、断裂韧性、轻量化三个维度给出可执行结论：7075铝骨架 + CF远端连杆 + 钛轴销 + PEEK功能件，按零件分工而非追求单一材料。
CMU's riMESA combines Consensus ADMM with the incremental robust solver riSAM to unite distribution, incrementality, robustness and weak communication: sharing variables instead of full graphs, dual decay, RWBP that lets stale consensus be overruled by fresh evidence, and non-blocking communication threads. Across 2430 synthetic and 28 real datasets, its gap to Centralized GNC is 7x smaller than DLGBP and 17x smaller than DDF-SAM2, at only ~55 KB/s average bandwidth.
