This is an excellent robotics survey paper contrasting deep learning “implicit” models (data driven) with the long history of “explicit” models (Good Old Fashioned Engineering) and calling for methods that integrate both: @BekrisKostas https://
arxiv.org/abs/2410.12172
ROBOTICS
-
Robotics Survey: Integrating Deep Learning and Explicit Engineering Models
By
–
-
EMP Shielding More Cost-Effective Than Drone Deployment
By
–
It’s cheaper to shield drone electronics than to deploy these things. EMP defenses aren’t really feasible.
-
Drones Shift Military Balance Toward Offensive Capabilities
By
–
Drones tip the balance of power towards offense, much like nuclear did. It may help to think of them as “autonomous bullets.”
-
Drone Proliferation and Mutually Assured Destruction Dynamics
By
–
Drone proliferation will democratize Mutually Assured Destruction and possibly lead to an uneasy peace.
-
Comparing π_0 Robot Training Data to Qwen LLM Training Scale
By
–
Thanks Kevin! Using your conversion rate, that works out to π_0 trained on 1 person-year of robot data vs. Qwen trained on 120,000 person-years of LLM data:
-
Generative Video WorldSim: Sora, Genie, VideoPoet Deep Dive
By
–
Generative WorldSim, Diffusion, Vision, Reinforcement Learning and Robotics Our longest episode ever! https://
latent.space/p/icml-2024-vi
deo-robots
… a deep dive into
– @OpenAI Sora (with @billpeeb
), – DeepMind Genie with @jparkerholder and @ashrewards – VideoPoet with @hyperparticle – -
Toyota CUE6 robot breaks basketball distance record with AI learning
By
–
El robot humanoide CUE6 de Toyota ha batido el récord de distancia de tiro en baloncesto con una impresionante distancia de 24,55 metros. Este logro lo convierte en el robot que es capaz de encestar desde más distancia.
— Juan Merodio (@juanmerodio) 9 décembre 2024
Usa la inteligencia artificial para aprender de sus errores… pic.twitter.com/oaDoAWqY4AEl robot humanoide CUE6 de Toyota ha batido el récord de distancia de tiro en baloncesto con una impresionante distancia de 24,55 metros. Este logro lo convierte en el robot que es capaz de encestar desde más distancia. Usa la inteligencia artificial para aprender de sus errores
-
Navigation World Models: Video Generation for Autonomous Agent Planning
By
–
Navigation World Models A controllable video generation model that predicts future visual observations for navigation tasks based on past observations and actions. Problem: Visual-motor agents struggle with planning flexible navigation trajectories, especially in dynamic or
-
WordPress categories focused on AI topics
By
–
For anyone else reading along, tested this idea in a new post: