robotics
PulseAugur coverage of robotics — every cluster mentioning robotics across labs, papers, and developer communities, ranked by signal.
- instance of ScienceCast 70%
- used by CORE Recommender 70%
- instance of CatalyzeX Code Finder for Papers 70%
- used by ScienceCast 70%
- developed DagsHub 70%
- used by Gotit.pub 70%
- developed Gotit.pub 70%
- developed ScienceCast 70%
- instance of autonomous driving 70%
- instance of Embodied Ai 70%
- used by Vision-language-action model 70%
- instance of computer science 70%
- 2026-07-16 research_milestone Researchers introduced RoboTTT, a robot model and training recipe that scales visuomotor context to 8K timesteps, enabling new capabilities like one-shot imitation and improved performance on long-horizon tasks. source
22 day(s) with sentiment data
-
New framework boosts multi-agent communication efficiency for robotics
Researchers have developed a novel framework for multi-agent reinforcement learning systems that significantly improves communication efficiency in bandwidth-constrained environments. By integrating information bottlene…
-
New FACT Model Learns Robotics from Failed Actions
Researchers have developed FACT, a novel causal World-Action Model designed to improve robotics by learning from both successful and failed actions. Unlike previous models that primarily train on successful demonstratio…
-
New SG-WAM method improves robotic manipulation with language guidance
Researchers have introduced SG-WAM, a novel method designed to improve the accuracy of World-Action Models (WAMs) in robotics. Existing WAMs often struggle to align predicted actions and future videos with language inst…
-
PhysX-CoT: New method generates 3D assets with explicit physical reasoning
Researchers have introduced PhysX-CoT, a novel approach to generating simulation-ready 3D assets from single images. Unlike previous methods that treat this as an implicit vision-language task, PhysX-CoT explicitly mode…
-
New RAG-3DSG method enhances 3D scene graph accuracy for robotics
Researchers have developed RAG-3DSG, a novel method to improve the accuracy and semantic consistency of 3D Scene Graphs (3DSGs). This approach addresses issues like noise and ambiguity that arise from occlusions and lim…
-
AI cost savings questioned by healthcare professional
The author, working in healthcare, questions the assertion that AI and robotics will be cheaper than human labor. They observe that physical therapy clinics operate on very thin margins, and when attempting to quantify …
-
Webinar to explore reinforcement learning applications in robotics
Shawn Hymel will host a webinar on August 13th focusing on the application of reinforcement learning in robotics. The session will feature a demonstration of a simple balance bot, providing practical insights into the i…
-
New thesis tackles technical debt in AI-driven Cyber-Physical Systems
A new thesis explores the unique technical debt found in AI-intensive Cyber-Physical Systems (AI-CPS). These systems, used in areas like autonomous vehicles and healthcare, combine hardware, AI, and conventional softwar…
-
Eatable Adventures launches NOVO Agrifoodtech accelerator in Bilbao
Eatable Adventures has launched NOVO Agrifoodtech, a new accelerator program based in Bilbao. This equity-free initiative focuses on deeptech startups, aiming to integrate advanced technologies like AI, biotechnology, a…
-
Online learning refines wind tunnel airflow for enhanced robot flight
Researchers have developed an online learning algorithm to precisely control airflow in a vertical wind tunnel for testing advanced aerial robots. This method combines a simplified physical model with iterative learning…
-
New mixed-reality system ORCESTRA enables VLM-driven robot programming
A new mixed-reality system called ORCESTRA has been developed for programming robot digital twins. This system allows users to interact with robot twins in a passthrough mixed-reality environment, enabling them to teach…
-
Samsung details Galaxy Z Fold 8 design; Trump's AI policies affect robotics
Samsung has revealed that the new shape of its Galaxy Z Fold 8 is a deliberate design choice, emphasizing that a single form factor cannot cater to all users. The company also discussed color options for its foldable de…
-
US bans foreign robots to protect AI industry, sparking debate
The Federal Trade Commission (FTC), influenced by a Trump-aligned administration, has implemented a ban on foreign imports of advanced robots, including humanoids and quadrupeds. This policy aims to protect the nascent …
-
Robotics expert details reinforcement learning for robot simulation and training
Shawn Hymel has released a new video and is hosting a webinar on reinforcement learning for robotics. The video, part 2 of a series, covers Proximal Policy Optimization (PPO) and demonstrates training an agent to balanc…
-
ChinaTalk launches $50k contest for AI and US-China relations research
ChinaTalk is launching a $50,000 submission and hiring contest focused on emerging technologies and their implications for US-China relations. The contest, supported by a grant from Coefficient Giving, invites proposals…
-
New framework defines trustworthiness for embodied AI systems
A new systems framework for trustworthy embodied intelligence has been proposed, integrating perception, decision-making, and physical interaction. This framework emphasizes sustained safe success by organizing mechanis…
-
Daniela Rus wins Germany's top tech prize for AI and robotics
Daniela Rus has been honored with Germany's prestigious Minister-President's High-Tech Prize for her three decades of pioneering work in robotics and artificial intelligence. Her research has led to significant advancem…
-
New DLAM model enhances robot action learning from video data
Researchers have introduced DLAM, a new distributional latent-action model designed to improve the learning of robot actions from video data. Unlike previous methods that use deterministic transitions, DLAM represents e…
-
New self-adaptive learning method tracks unknown dynamics
Researchers have developed a novel self-adaptive online learning method for control systems designed to track unknown and potentially switching target dynamics. This method simultaneously learns multiple predictors and …
-
Indian startup sells housekeeper video data for AI training
Pronto, a startup operating in India, is generating revenue by selling video data captured by housekeepers wearing head-mounted cameras to AI companies. This initiative, called Pronto Verified, aims to provide diverse r…