NVIDIA Isaac Sim
PulseAugur coverage of NVIDIA Isaac Sim — every cluster mentioning NVIDIA Isaac Sim across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
AI safety debate shifts to adversarial attacks and system control
The AI safety debate is intensifying, with a focus shifting from preventing system failures to addressing adversarial attacks that manipulate AI behavior. Researchers are developing methods to test robot safety against …
-
NVIDIA open-sources OSMO for unified AI robotics development
NVIDIA has open-sourced OSMO, a Kubernetes-native workflow orchestrator designed to streamline the development of physical AI. This tool allows robotics teams to define training, simulation, and robot testing pipelines …
-
Annu Intelligence launches six models to enable industrial embodied AI deployment
Annu Intelligence has released six models designed to address the challenges of deploying embodied AI in industrial settings. These models cover data generation, cognitive understanding, training, action execution, and …
-
New synthetic dataset WireSeg-32K improves wire instance segmentation
Researchers have introduced WireSeg-32K, a synthetic dataset designed to improve wire instance segmentation. This dataset comprises 32,000 images with instance masks and depth maps, generated using a co-simulation pipel…
-
AI 3D firm VAST secures 3B RMB funding, launches Tripo P2.0 model
VAST, a leading AI company focused on 3D technology, has successfully raised approximately 3 billion RMB in its Series B and B+ funding rounds, bringing its total funding in under six months to around 5 billion RMB. Thi…
-
New Orbit-Planner model enhances satellite obstacle avoidance
Researchers have developed Orbit-Planner, a novel two-stage latent world model designed for satellite agents to navigate and avoid obstacles in orbit. This model learns action-conditioned spacecraft dynamics to predict …
-
Robotics & Physical AI Careers: New Grad Job Market & Skills Advice
A final-year student specializing in Physical AI and Robotics is seeking advice on the current job market for entry-level positions in this field. The student has a strong technical background including simulation tools…
-
Robotics firms face 10x compute surge, turning to cloud for R&D efficiency
Robotics companies are experiencing a tenfold increase in computational demand over two years, driven by the integration of large models that enable robots to understand and reason. This surge necessitates a shift from …
-
New GAUGE benchmark tests physical fidelity in AI simulators
Researchers have introduced GAUGE, a new benchmark designed to evaluate the physical fidelity of both simulation engines and generative video world models. This benchmark is grounded in real-world physics and includes 2…
-
New Spatial-IQ framework tests LLM spatial reasoning capabilities
Researchers have introduced Spatial-IQ, a new hierarchical framework designed to deconstruct and test the spatial reasoning capabilities of multimodal large language models (MLLMs). This framework breaks down object cou…
-
New RL frameworks bridge sim-to-real gap for quadruped locomotion · 2 sources tracked
Researchers have developed new reinforcement learning (RL) frameworks for quadrupedal locomotion, addressing the sim-to-real gap. The first approach, utilizing NVIDIA's Isaac Sim and Isaac Lab, achieves zero-shot sim-to…
-
EVIS plugin generates physics-grounded event camera data for NVIDIA Isaac Sim
Researchers have developed EVIS, a new plugin for NVIDIA Isaac Sim that generates physics-grounded event camera data. This tool addresses the scarcity of labeled event-camera data by creating high-rate, fully labeled ev…
-
New GraspIT dataset bridges sim-to-real gap for robotic grasping
Researchers have introduced GraspIT, a new dataset designed to improve robotic grasping by bridging the gap between simulation and real-world applications. The dataset features tabletop scenes with photorealistic RGB-D …
-
New pipeline enhances synthetic-to-real domain adaptation for object detection
Researchers have developed a new pipeline called SmartSDG, built on NVIDIA Isaac Sim and utilizing Physically-Based Shading (PBS), to improve the transfer of object detection models from synthetic to real-world data. Th…
-
New benchmark SoftVTBench evaluates robotic manipulation safety
Researchers have introduced SoftVTBench, a new benchmark designed to evaluate robotic manipulation of deformable objects, focusing on both task completion and physical safety. This benchmark, built using NVIDIA Isaac Si…
-
New models enhance robot manipulation by integrating vision and state
Researchers have developed several new methods to improve robot manipulation capabilities by better integrating visual information with the robot's state and actions. GeoProp, for instance, is a lightweight adapter that…
-
Nuwa Robotics raises millions for 'World Travelers Model' in embodied AI
Nuwa Robotics, a Chinese embodied intelligence company, has secured tens of millions of yuan in angel and seed funding. Founded by Dr. Yang Ruigang, formerly of Baidu's autonomous driving and robotics lab, the company i…
-
New pipeline enhances synthetic-to-real domain adaptation for object detection
Researchers have developed a new pipeline called SmartSDG, built on NVIDIA Isaac Sim and utilizing Physically-Based Shading (PBS), to improve the transfer of object detection models from synthetic to real-world data. Th…
-
New dataset tackles robotic strawberry harvesting pose estimation
Researchers have developed a new dataset and baseline for 6D pose estimation specifically for robotic strawberry harvesting. This dataset, comprising 12,040 real-world images collected from agricultural fields, addresse…
-
Spiking neural network integrates arm and leg control for humanoid robots
Researchers have developed a novel spiking neural network architecture capable of coordinating both arm and locomotor control in humanoid robots. This system integrates force-based arm control with bipedal locomotion, m…