Interesting Engineering

Humanoid robot walks across sand, gravel and slopes using faster training framework

Georgia Tech's new machine-learning framework helps humanoid robots master rough terrain using faster, cheaper training.
Interesting Engineering

MIT: Robots gain real-world skills through lifelike 3D virtual environments

MIT's SceneSmith creates realistic 3D worlds where robots safely train, reducing costs and speeding AI-powered robot ...
IEEE

Learning Accurate Robot Dynamics From Position-Only Data With Discrete Lagrangian Neural Networks

Abstract: Achieving high-fidelity modeling of robot dynamics remains a major challenge in scientific computing and artificial intelligence. Black-box models are prone to overfitting and lack ...
IEEE

Safety-Critical Learning of Robot Control With Temporal Logic Specifications

Abstract: Reinforcement learning (RL) is a promising control approach in many scenarios. However, safety-critical applications are still a challenge due to lack of safety guarantees during exploration ...