Technical Directions
Robotics coverage relating to robot policies.
776 selected reportsLast 30 days 662 recordsAll coverage 3,792 records
This paper presents FineART, a densely annotated bimanual manipulation dataset with 40,543 episodes and 533,913 subtask labels, totaling 1,718 hours. It also introduces FineART-VLA, a vision-language-action policy that improves task success rates through dense subtask training. The dataset and model are open-sourced, offering a new benchmark for long-horizon bimanual manipulation tasks.
Before humanoid robots mature, Physical AI is attempting to enter industrial scenarios still reliant on manual operations by deploying on mature robotic arms. Companies like Sanctuary AI and Skild are integrating AI models into robotic arms from different manufacturers to perform complex tasks such as wire insertion.
The source reports AMD’s acquisition of World Labs, co-founded by Fei-Fei Li, for approximately ¥55 billion, and Megmeet’s proposed ¥664 million acquisition of a welding subsidiary. It also covers funding and listing activity among Chinese robotics companies. These are the publisher’s reports, not independently verified transactions.
This paper presents LeaP, a learnable source prior for generative robot policies, which replaces fixed standard Gaussian distributions with state-dependent random initialization. LeaP jointly learns the mean and variance of an initial Gaussian distribution, improving action generation in robotic tasks. The method achieves an average success rate of 81.6% in simulation and 80.0% on real robotic arms, outperforming existing baselines like A2A and VITA. The paper is accepted at CoRL 2026, and the code is open-sourced.
To address the issue of insufficient warehouse space, Figure AI decided to melt down the F.02 robot instead of disassembling or selling it. This decision involves multiple considerations, including intellectual property protection, technical confidentiality, and asset management. Although the destruction process faced challenges in terms of site and technology, it was ultimately completed at the Finnish factory. This incident has also sparked discussions about the management of retired robots and industry standards.
Professor Shi Qing's team from Beijing Institute of Technology was inspired by the high-speed running mechanism of the elephant shrew. They designed a micro quadruped robot named FLEXOR equipped with a dual-joint coupled spine. Through dynamic spine-leg coordination, the robot achieved a 31.6% increase in speed and a 32.2% reduction in energy consumption without upgrading its motors. The study reveals the critical role of the timing coordination between the spine and legs in locomotion performance and verifies the universality of this mechanism across different robot morphologies, providing new insights for highly mobile embodied intelligent robots.
Destro AI, a startup with an $8 million seed round, is redefining robotics deployment by creating an AI intelligence layer that coordinates both human workers and robots in logistics settings. Their system, called Mothership, streamlines cross-docking operations by directing humans, carts, and trucks through a unified workflow, offering a more efficient alternative to traditional automation and competing robotic startups.
Aaron Ames, a leading roboticist at Caltech, argues that safety must be the primary concern for humanoid robots. He emphasizes the need for formal mathematical guarantees, such as control barrier functions (CBFs), to ensure safe operation. Ames highlights the gap between impressive demonstrations and real-world safety, urging the industry to prioritize safety standards to prevent harm.
The Stanford team's HomeBody project demonstrates how GPT-6 Astra controls the Unitree G1 robot to complete kitchen cleaning tasks through a three-step process: spatial exploration, digital twin simulation, and task execution. The system uses pre-trained models and a skill library to perform complex operations in new environments without additional training.
AGIBOT Robotics has deployed 100 units of the Lingxi X2 humanoid robot in 100 retail stores of Aishida, achieving a 39% increase in store sales. The robots, named 'Aibao,' engage customers by understanding their cooking needs and guiding them toward suitable products, while also seamlessly transferring conversations to human staff when necessary. This marks a milestone in the deployment of embodied AI in real-world retail environments.
Robotic Systems Lab@leggedroboticsSignalEditorial score7878
Carnegie Mellon University and Siemens developed PRISM, a method to assess the safe stoppability of humanoid robots. The approach uses simulation to define safe stopping conditions, enabling proactive safety monitoring and supporting certification of fail-safe behaviors. The research highlights the importance of context in determining when a robot can be safely stopped, especially in environments with people or obstacles.
Carnegie Mellon University researchers have developed LAMP, a system that allows multiple robots to work together to move objects through crowded spaces. LAMP combines learned models with search-based planning to enable efficient navigation and coordination, with successful testing in complex environments and a demonstration at the 2026 IROS conference.
Animesh Garg@animesh_gargSignalEditorial score7878Introducing FLUX 3 Action. An open weights 7B World Action Model that achieves first place on the RoboLab benchmark. It outperforms the previous best open model by 6.1 percentage points while using 56% fewer parameters and running up to 3.95x faster. FLUX 3 Action removes the usual trade-off between world action model performance and VLA speed: it still predicts video and actions together, but plans more than twice as far ahead and runs faster per second of robot motion than the strongest open VLA. Teams can fine-tune FLUX 3 Action on their own demonstrations to create policies for a particular robot and task. Together with @nvidia, we also integrated FLUX 3 Action natively into @huggingface's LeRobot, with fine-tuning recipes included and edge deployment on NVIDIA Jetson. Beyond robotics, we’re also seeing promising results training task-specific policies for acting in simulated environments like gaming, controlling a vehicle, computer use, and wherever else a model needs to understand a visual environment and then choose what to do next. FLUX 3 Action builds on the same image, video, and audio pretraining as FLUX 3, but uses a smaller architecture designed for practical deployment. In midtraining, we trained the model to predict actions and future frames together. We’re releasing the weights, code, fine-tuning recipe, benchmarks, and reproducible examples so researchers and developers can build on the model with their own robots, environments, and tasks (see below).
China is pursuing a strategic roadmap through its Five-Year Plans to dominate the global robotics industry, focusing on embodied AI and humanoid robotics. The 13th and 14th FYPs laid the foundation for industrial automation, while the 15th FYP emphasizes embodied intelligence, with state support for R&D and mass deployment of humanoids. Despite achievements in market share and production scale, challenges remain in precision hardware and semiconductor self-sufficiency, with risks of overcapacity and market volatility.
Robotic Systems Lab@leggedroboticsSignalEditorial score7878
NVIDIA Isaac ROS 5.0, released at ROSCon 2026, enhances open source robotics development with agentic workflows, GPU acceleration, and new skills for perception and manipulation. It supports ROS Lyrical and Ubuntu 24.04, enabling developers to build and deploy high-performance robotics applications using NVIDIA's accelerated computing and AI models.
Researchers at the University of Michigan and UCLA have developed a new propulsion mechanism for small robots using low-power twisting of elastic rods. This method enables hopping and swimming motions by utilizing snapping mechanics. The mechanism works on challenging surfaces such as slippery cloth and grass-covered ground, producing frog-like motion. The study, published in Science Advances, was co-led by Khalid Jawed and Xiaonan (Sean) Huang, and demonstrates the potential for miniature robots to maneuver over uneven or slippery terrain.
MIT researchers have developed a reconfigurable robotic lab that autonomously assembles, tunes, and dismantles optical experiments. The system uses robotic arms, 3D-printed component housings, and a cloud-based interface to enable remote operation. It can build and fine-tune a laser cavity in under 30 minutes, demonstrating the potential for fully automated optical experiments.
Researchers at ETH Zurich have developed a robotic platform with a magnetically controllable endoscope to improve the safety and precision of fetal surgery for twin pregnancies with shared placentas. The system uses magnetic fields to bend the endoscope, enabling better access to blood vessels, and combines panoramic imaging with real-time navigation. The technology has been tested in an animal model and is now being refined for human clinical use.
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).