Technology areas
Grasping and manipulation
Grasping, dexterous hand manipulation, dual-arm coordination, assembly, contact-rich manipulation, deformable objects, tool use, and mobile manipulation. The focus is changing an object's state or completing a manipulation task. Hand mechanisms and joint hardware belong under Robot hardware and key components.
96 selected · 47 in the last 30 days
Physical Intelligence ·
Physical Intelligence releases steerable general-purpose robot model π0.7, demonstrating compositional generalization
Physical Intelligence has released the general-purpose robot model π0.7, which it says can perform a variety of dexterous manipulations with speed and robustness comparable to fine-tuned specialized models, and shows preliminary signs of compositional generalization on tasks not seen in its training data.
Dexterity ·
Dexterity launches Instinct tactile intelligence system
Dexterity announced the launch of Instinct, a tactile intelligence system that reads force at 500–2000 Hz and responds in 0.5–2 ms to perform force-guided bin packing on production lines, with a median placement time of 4.55 seconds and an overall team success rate of 81% (95% CI 75%–86%, sampled from 854 placements). Placements that cannot be completed are quickly identified and handed back to the Foresight world model to retry with a different angle or position; the same skill delivers consistent performance across different robotic arm hardware and generalizes to objects of different materials.
PsiBot/灵初智能 ·
Lingchu Intelligence Releases Psi-R2 and Psi-W0 Dual Models, Pretrained on 100,000 Hours of Human Data
Lingchu Intelligence released two models, Psi-R2 and Psi-W0, which it calls the industry's first embodied intelligence models pretrained on human data at the 100,000-hour scale.
Berkeley AUTOLAB ·
CaP-X: Benchmarking and Improvement Framework for Robot Manipulation Coding Agents Released
Teams including Berkeley AUTOLAB propose CaP-X, an open framework for systematically studying Code-as-Policy agents in robot manipulation, centered on the interactive environment CaP-Gym and CaP-Bench, which evaluates 12 frontier models.
松灵机器人 ·
NYU open-sources YOR, a low-cost dual-arm mobile robot, with bill of materials under $10,000
A research team at New York University has open-sourced YOR (Your Own Robot), a mobile dual-arm manipulation robot, with a bill of materials cost below $10,000. The project homepage is www.yourownrobot.ai, and the paper is at arxiv.org/abs/2602.11150.
Dexterity ·
Dexterity details evaluation methods and production metrics for the Foresight packing agent
Dexterity published an article introducing system evaluation and production measurement for the Foresight packing agent. On the planning side, it was tested on four real warehouse box-type distributions, with density of 0.65–0.77 and stability of 99.7–100%, and distribution-free order statistics were used to give 95% confidence intervals; the article also found that randomly shuffling the box sequence causes local variance to collapse by about 1.4 times, making evaluation overly optimistic.
Physical Intelligence ·
Physical Intelligence proposes RLT: efficient online reinforcement learning for fine manipulation
Physical Intelligence proposes a new method called RL tokens (RLT), in which a vision-language-action model (VLA) outputs a special token to interface with a lightweight online reinforcement learning policy, improving the speed and success rate of fine manipulation phases with only a small amount of real data.
Skild AI ·
Skild AI partners with ABB Robotics, Universal Robots, and NVIDIA to deploy Skild Brain
Skild AI announced partnerships with ABB Robotics and Teradyne-owned Universal Robots and MiR to integrate its general-purpose model Skild Brain into industrial robots, eliminating task-by-task programming and using post-training fine-tuning with a small amount of task data.
Physical Intelligence ·
Physical Intelligence proposes MEM, enabling π0.6's VLA to remember long-horizon tasks of up to 15 minutes
Physical Intelligence proposed a method called Multi-scale Embodied Memory (MEM) that provides vision-language-action models (VLAs) with both short-term and long-term memory, enabling the model to complete tasks lasting up to 15 minutes, such as cleaning an entire kitchen or making a grilled cheese sandwich from scratch.
Physical Intelligence ·
Physical Intelligence proposes a physical intelligence layer and publishes π 0.6 deployment data from Weave and Ultra
In a blog post, Physical Intelligence argues that robots need a reusable physical intelligence layer, and it published real-world deployment data from partners Weave and Ultra using π 0.6.
Figure AI ·
Figure AI Releases Helix 02: A Full-Body Autonomous Control Model for Humanoid Robots
Figure AI has released Helix 02, extending control from the upper body to the entire humanoid robot and enabling continuous, integrated autonomous tasks combining locomotion and manipulation. It adds a new System 0 whole-body controller, trained on over 1,000 hours of human motion data and simulation-based reinforcement learning, which outputs joint commands at 1 kHz via a 10M-parameter network, replacing roughly 109,504 lines of hand-written C++ code; System 1 connects head-mounted vision, palm cameras, fingertip touch sensing, and proprioception, outputting whole-body joint targets at 200 Hz.
Diligent ·
Serve Robotics to acquire Diligent Robotics, expanding autonomous robotics platform to indoor hospital settings
Serve Robotics announced it has signed an agreement to acquire Diligent Robotics, with consideration consisting of $29 million in the company's common stock paid to Diligent shareholders (subject to adjustments such as net debt), plus up to $5.3 million in milestone earnouts. The deal is expected to close in the first quarter of 2026, and Diligent will continue to operate as a Serve subsidiary under the leadership of Andrea Thomaz.
Physical Intelligence ·
Physical Intelligence fine-tunes π 0.6 to take on five Robot Olympics tasks, winning three golds and two silvers
By fine-tuning its latest π 0.6 model, Physical Intelligence achieved preliminary solutions for the gold-medal tasks in 3 of the five everyday manipulation challenges in the Robot Olympics proposed by Benjie Holson, and reached silver-medal level in the remaining 2, with an average success rate of 52% and task progress of 72%.
Sharpa ·
Sharpa announces mass production of SharpaWave dexterous hand, to exhibit at CES 2026
Sharpa announced that mass production of its flagship dexterous hand, SharpaWave, has begun, with early customers including global technology companies and research universities.
LimX Dynamics ·
LimX Dynamics launches multi-form embodied robot TRON 2, open for pre-order from 49,800 yuan
LimX Dynamics has launched the multi-form embodied robot TRON 2, whose single body can quickly switch between three configurations: dual-arm, bipedal, and dual-wheel-legged. It is priced from 49,800 yuan and is open for pre-order starting today. The dual-arm configuration is a 7-DoF humanoid design with a 70 cm arm span and a 10 kg dual-arm payload, and the body has a maximum load capacity of 60 kg. In bipedal form it has a 4-hour battery life and a maximum payload of 30 kg, and it can perceive its surroundings and climb stairs.
Figure AI ·
Figure AI releases third-generation humanoid robot Figure 03
Figure AI has released its third-generation humanoid robot, Figure 03, redesigned from the ground up for the Helix VLA model, the home, and large-scale mass production, covering both software and hardware.
LimX Dynamics ·
GVF-TAPE Algorithm from LimX Dynamics and Partners Accepted to CoRL 2025, Enabling Robots to Learn Manipulation from Video
The paper "Generative Visual Foresight Meets Task-Agnostic Pose Estimation in Robotic Table-top Manipulation," a collaboration between SUSTech CLEAR Lab, LimX Dynamics, and the University of Hong Kong, has been accepted to CoRL 2025.
Figure AI ·
Figure AI's Helix model achieves fully autonomous towel folding on a humanoid robot
Figure AI's VLA model Helix fully autonomously folds towels, which the company says is the first time a multi-fingered humanoid robot has completed this task using an end-to-end neural network. With the architecture and training hyperparameters unchanged and only a new dataset added, it can pick items from a mixed towel pile, adjust its folding strategy based on the initial shape, correct multiple grasping errors, and untangle twisted towels using fine motions such as tracing edges with its thumb and pinching corners.
Figure AI ·
Figure AI reports three-month Helix logistics deployment progress: 4.05 seconds per item, about 95% barcode success rate
Figure AI released progress on Helix's capabilities after three months of deployment in a logistics environment: per-item processing time fell from about 5.0 seconds to 4.05 seconds, barcode scanning success rate rose from about 70% to about 95%, and the system gained the ability to handle flexible packages such as poly bags and flat envelopes.