Vision-Language-Action Models Arrive


The AI model type capturing the most attention across robotics and autonomous vehicles right now is the vision-language-action model, or VLA. At embedded AI conferences this year, particularly the recently held Embedded Vision Summit, VLAs were a main topic of discussion – not as a research curiosity, but as the architecture that teams building autonomous systems are actively targeting. If yo... » read more

AI Accelerator Testing Depends On DFT Innovations


Key Takeaways: I/O and lane repair capabilities are becoming critical to improving yield. System-level testing catches marginal defects and rare defects such as silent data corruption errors. Synopsys and TSMC developed a multi-die demo vehicle capable of full test, monitor, debug, and repair capability across the system’s lifecycle. The proliferation of accelerators in AI... » read more

Humanoid Touch And Voice Are Improving Rapidly


Key Takeaways Humanoid robots are rapidly expanding beyond factories and logistics toward broader, general-purpose roles (including in-home assistance), driven by advances in AI and sensing. Compared with vision and language, touch (haptics) and hearing/voice in real environments remain the hardest — and most commercially important — sensing challenges, requiring fast sensor fusio... » read more

Rethinking Robotics Reinforcement Learning: A Practical Humanoid Training Workflow


Reinforcement learning (RL) for robotics is often associated with large GPU clusters, distributed infrastructure, and x86-based development environments. Training a humanoid robot with high-fidelity simulation is a resource-intensive workflow that runs in the data center. What if that workflow could run on a single workstation? In this blog post, we explore a complete robotics pipeline bu... » read more

Enabling Physical AI and Robotics: Platform for the Intelligent Edge


Physical AI has emerged as an essential technology driving the future of robotics — it closes the loop between perception, reasoning, and action in the real world using powerfully trained AI models. But for robots and autonomous machines, that loop only works well if it runs where the world is actually sensed: at the Edge. Instead of streaming raw sensor data to a data center for interpretati... » read more

Limiting AI/ML Tools To Ensure Physical AI Safety, Security


Key Takeaways: AI-based tools can help monitor physical AI systems and LLMs, but human oversight is still needed to avoid false positives, bias, and other anomalies. For autonomous vehicles and robots, edge case scenarios and understanding human values are weak points, especially as moral and social values change over time. AI tools are growing and becoming increasingly helpful for c... » read more

Digital Engineering Drives Industry 5.0


During the Fourth Industrial Revolution, known as Industry 4.0, industrial processes and manufacturing shifted toward digitization in nearly every market, from agriculture and mining to heavy machinery and building automation systems. Today, this digital transformation is not slowing down. A global industrial robotics survey from McKinsey & Co. revealed that industrial companies are expecte... » read more

Physical AI Takes Functional Safety Cues From Automotive


Robots are becoming smarter, more capable, and more pervasive, setting the stage for a whole new round of growth that will touch nearly every part of the semiconductor and software industries for decades to come. Robots are at the core of physical AI, a broad segment of edge AI systems that interact with the world through artificial intelligence and sensors. This includes everything from hum... » read more

LLMs Add Safety Risks To Physical AI


Humanoid robots with artificial general intelligence are some years from entering our daily life, but application-specific robotics are already here. From Amazon’s fleet of fulfillment center robots to robotic surgical systems in operating rooms, search and rescue robo-dogs, autonomous drones, and last-mile delivery robots, all the way down to the humble Roomba vacuum cleaner, physical AI sys... » read more

Classical Computing vs. Machine Learning and Edge AI Techniques in Various Application Domains


Machine Learning (ML) algorithms have revolutionized various domains by enabling data-driven decision-making and automation. The deployment of ML models on embedded edge devices, characterized by their constrained computational resources and low power requirements, presents unique challenges and opportunities. As the digital world continues to generate increasingly complex and high-volume da... » read more

← Older posts