Tesla HQ pic taken this morning
ROBOTICS
-
TacSL: Library for Visuotactile Sensor Simulation and Learning
By
–
TacSL
— AK (@_akhaliq) 14 août 2024
A Library for Visuotactile Sensor Simulation and Learning
discuss: https://t.co/LznliHFNRs
For both humans and robots, the sense of touch, known as tactile sensing, is critical for performing contact-rich manipulation tasks. Three key challenges in robotic tactile… pic.twitter.com/yxeq1GDZ5MTacSL A Library for Visuotactile Sensor Simulation and Learning discuss: https://
huggingface.co/papers/2408.06
506
… For both humans and robots, the sense of touch, known as tactile sensing, is critical for performing contact-rich manipulation tasks. Three key challenges in robotic tactile -
Foundation Models and Gemini Transform Robotics Research
By
–
Very excited about the huge potential of applying foundation models to robotics, & Gemini is perfect for this bc it’s natively multimodal. Some cool recent experiments below. If you're interested to work at the frontier of robotics, the @GoogleDeepMind robotics team is hiring! https://t.co/R4zRQmLEp7
— Demis Hassabis (@demishassabis) 13 août 2024Very excited about the huge potential of applying foundation models to robotics, & Gemini is perfect for this bc it’s natively multimodal. Some cool recent experiments below. If you're interested to work at the frontier of robotics, the @GoogleDeepMind robotics team is hiring!
-
Google Robotics Team Achieves Landmark Competitive Table Tennis Performance
By
–
Amazing work from our robotics team on this extremely tricky physical challenge of playing table tennis. Huge congrats to @lgraesser3 , @samindaa, @Evo_Daveo, @pannag_ and team on this landmark result! Read more here: https://t.co/1JnIBKMkAO https://t.co/lTTS7X6vx4
— Demis Hassabis (@demishassabis) 13 août 2024Amazing work from our robotics team on this extremely tricky physical challenge of playing table tennis. Huge congrats to @lgraesser3 , @samindaa
, @Evo_Daveo
, @pannag_ and team on this landmark result! Read more here: https://
sites.google.com/corp/view/comp
etitive-robot-table-tennis/home?utm_source=&utm_medium=&utm_campaign=&utm_content=
… -
Remote equipment operation improves worker safety in deep mines
By
–
Trabajar a 600 metros de profundidad no está exento de riesgos y por eso en la provincia china de Xinjiang los trabajadores operan el equipo pesado de manera remota desde una oficina.
— Juan Merodio (@juanmerodio) 11 août 2024
Un gran avance que hace su trabajo mucho más seguro. pic.twitter.com/c2tqNwqVwkTrabajar a 600 metros de profundidad no está exento de riesgos y por eso en la provincia china de Xinjiang los trabajadores operan el equipo pesado de manera remota desde una oficina. Un gran avance que hace su trabajo mucho más seguro.
-
FIRST Robotics Inspires PhD Student to Faculty Robotics Career
By
–
Not sure what age they are, but FIRST Robotics got both my daughters interested in robotics during high school. My older one finished her PhD in robotics and is now a faculty member doing RL and robotics
-
EES Enables Boston Dynamics Spot to Learn Complex Task in Hours
By
–
EES's knack for efficient learning was evident when implemented on Boston Dynamics’ Spot quadruped during research trials at The AI Institute.
— MIT CSAIL (@MIT_CSAIL) 9 août 2024
In one demo, the robot learned how to securely place a ball and ring on a slanted table in ~3 hours. pic.twitter.com/EgQO5EwLAOEES's knack for efficient learning was evident when implemented on Boston Dynamics’ Spot quadruped during research trials at The AI Institute. In one demo, the robot learned how to securely place a ball and ring on a slanted table in ~3 hours.
-
Algorithm Trains Robot to Sweep Toys Twice as Fast
By
–
In another, the algorithm guided the machine to improve at sweeping toys into a bin w/i about 2 hours.
— MIT CSAIL (@MIT_CSAIL) 9 août 2024
Both results appear to be an upgrade from previous methods, which would have likely taken >10 hours per task. pic.twitter.com/GAC6hrS8DVIn another, the algorithm guided the machine to improve at sweeping toys into a bin w/i about 2 hours. Both results appear to be an upgrade from previous methods, which would have likely taken >10 hours per task.
-
Robot Vision System Learns Task Execution Through Practice
By
–
EES first works w/a vision system that locates & tracks the machine’s surroundings. Then, the algorithm estimates how reliably the robot executes an action & if it should practice more.
-
Robot skill refinement through EES forecasting and vision feedback
By
–
EES forecasts how well the robot could perform the overall task if it refines that skill & finally it practices. The vision system then checks if that skill was done correctly after each attempt. pic.twitter.com/oGBoP8zUL5
— MIT CSAIL (@MIT_CSAIL) 9 août 2024EES forecasts how well the robot could perform the overall task if it refines that skill & finally it practices. The vision system then checks if that skill was done correctly after each attempt.