Links of the week #44
Automotive
Self-driving cars
While EMMA shows great promise, we recognize several of its challenges. EMMA's current limitations in processing long-term video sequences restricts its ability to reason about real-time driving scenarios — long-term memory would be crucial in enabling EMMA to anticipate and respond in complex evolving situations. Other key challenges to ensure safe driving behavior include EMMA not leveraging LiDAR and radar inputs, which requires the fusion of more sophisticated 3D sensing encoders, the challenge of efficient simulation methods for evaluation, the need for optimized model inference time, and verification of intermediate decision-making steps.?
Robotics
Materials science
This study targets the curation of a comprehensive materials database of mechanical properties that typically feature on a stress-strain curve: yield strength, ultimate tensile strength, Young’s modulus, fracture strength and ductility. Through an improved information-extraction pipeline, a database of 720,308 material properties with an overall precision of 82.03% has been presented
Simulation
"If you want to find the secrets of systems simulation, think in terms of energy, frequency and vibration."
CAD
Sharing insights on MBSE & System Simulation | Tech Cluster Lead | Lecturer
3 个月Thanks for the reference, Eric! Great links there!