Two down, three more to go in our Munich AI Lectures summer sprint! Last week, Ludovic Righetti from New York University highlighted the innovative integration of Model-Predictive Control (MPC) and Reinforcement Learning (RL) in robotics. He explained how MPC offers precise control while RL provides adaptability, creating a robust framework for complex robotic tasks. Combining these approaches can overcome individual limitations and enhance robotic motion and manipulation. Prof. Righetti also emphasized interdisciplinary openness and ethical considerations for AI and robotics researchers. Yesterday, Ivan Laptev from MBZUAI (Mohamed bin Zayed University of Artificial Intelligence) discussed the evolution and current challenges in image and video recognition. He highlighted how human pose estimation and object recognition have become standard, yet image recognition software can miss context if queried incorrectly. Prof. Laptev introduced ViViDex, a framework for teaching robots precise hand movements using human videos. ViViDex involves three steps: extracting human movements, teaching robots through these movements, and refining their skills using video data. This research significantly advances robotic capabilities for complex tasks. These lectures underscore the need to view robotics and AI from diverse perspectives, combining insights from various researchers and disciplines to make meaningful progress. We are excited to see what Alexei (A.) Efros will add to the conversation in his highlight lecture ‘We are (still?) not giving data enough credit’ on July 17th - Sign up now! https://lnkd.in/eFH5iNJU #AI #computerVision #robotics #munichAILectures #baiosphere
baiosphere’s Post
More Relevant Posts
-
🤖 Researchers at the University of Cambridge have developed a groundbreaking robotic sensor with artificial intelligence that reads braille at DOUBLE the speed of most human readers! 📚 Using machine learning algorithms, the robot achieved an impressive 315 words per minute with nearly 90% accuracy. 🚀 While not initially designed for assistive purposes, the high sensitivity required for braille reading positions this technology as a fantastic testing ground for developing robot hands or prosthetics with human-like fingertip sensitivity. 👋 Human fingertips are incredibly sensitive, detecting subtle changes in texture and providing valuable information about the world. Replicating this level of sensitivity in a robotic hand is a major engineering challenge, but the Cambridge researchers have made significant strides! The team used an off-the-shelf sensor with a camera to create a more realistic and efficient robotic braille reader. Through machine learning algorithms, the robot can 'deblur' images of braille characters, achieving a reading speed and accuracy comparable to human readers. This development opens doors for applications beyond braille, such as detecting surface textures or slippage in robotic manipulation. 🌐 ✨ Kudos to the researchers at the University of Cambridge for pushing the boundaries of robotics and AI! 🙌 🔬 Read more: https://lnkd.in/deU-_HgB #DataSpike #Robotics #AI #Innovation #Technology #Research #CambridgeUniversity #ArtificialIntelligence #BrailleReading #RoboticsInnovation
To view or add a comment, sign in
-
Good morning, there are some PhD positions available to work in our group (https://rai.site.hw.ac.uk/), working at the The National Robotarium. The stipend is above the UK rate. If you are UK or EU citizen and would be interested in working with us, please send me a message. See below the theme of the PhDs. Thank you. Fernando. Theme: Research aims to revolutionize human-robot collaboration in industrial settings by integrating artificial intelligence (AI), reinforcement learning (RL) and systems monitoring. The objective is to develop an advanced framework that enables fluent and intuitive interaction between human workers and robotic agents in an industrial environment. The research will focus on leveraging AI to enhance perception capabilities, allowing robots to understand human gestures, intentions, activities, and dynamic task requirements not only allowing for seamless collaboration between human and robotic agents but also for a full digital record of the manufacturing environment including parts, people and robotics. Reinforcement learning will be employed to enable robots to adapt and optimize their actions based on real-time feedback, fostering a seamless collaboration where robots become responsive partners in complex industrial workflows. In addition natural language models will be employed to allow for seamless communication between human and robotic agents. Anticipated outcomes include improved task fluidity, reduced response times, and enhanced adaptability to dynamic manufacturing environments.
To view or add a comment, sign in
-
Best Universities in the USA for Robotics Master's program https://lnkd.in/ghyBYCNw These universities stand out as leaders in the realm of Robotics Master's programs, providing a combination of theoretical knowledge, hands-on experience, and access to cutting-edge research. Aspiring roboticists can find an ideal environment for innovation, collaboration, and personal growth at these institutions, shaping the future of robotics on a global scale. #UniversitiesinUSA #RoboticsProgram #MechanicalEngineering #ArtificialIntelligence #AI #AINews #AnalyticsInsight #AnalyticsInsightMagazine
To view or add a comment, sign in
-
Decision making under uncertainty is a key feature of the human intellect and a persisting grand challenge of AI research. Proper treatment of uncertainty plays a crucial role in robotic systems, spanning from robust vision to safe trajectory planning and optimal high-level control. Markus Heinonen, Erhan Oztop, and I invite submissions to our special issue "Uncertainty in Robotics" hosted by Frontiers in Robotics and AI, a well-known venue by robotics researchers. Once again, we promise a quick and high-quality review process. Visit the submission portal below to proceed: https://lnkd.in/dAuq8n4n Abstract submission DL: 15 September 2023 Paper submission DL: 20 November 2023
Uncertainty in Robotics
frontiersin.org
To view or add a comment, sign in
-
The Rise of Cognitive Robotics: Merging Artificial Intelligence and Robotics The Rise of Cognitive Robotics: Merging Artificial Intelligence and Robotics Introduction: In recent years, the field of robotics has witnessed a significant transformation with the integration of artificial intelligence (AI) techniques. This convergence has given birth to a new era of robotics known as cognitive robotics. Cognitive robotics combines the power of AI algorithms with […] https://lnkd.in/dZhFc33v
The Rise of Cognitive Robotics: Merging Artificial Intelligence and Robotics
To view or add a comment, sign in
-
The Rise of Cognitive Robotics: Merging Artificial Intelligence and Robotics The Rise of Cognitive Robotics: Merging Artificial Intelligence and Robotics Introduction: In recent years, the field of robotics has witnessed a significant transformation with the integration of artificial intelligence (AI) techniques. This convergence has given birth to a new era of robotics known as cognitive robotics. Cognitive robotics combines the power of AI algorithms with […] https://lnkd.in/dZhFc33v
The Rise of Cognitive Robotics: Merging Artificial Intelligence and Robotics
To view or add a comment, sign in
-
from NYU Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack https://lnkd.in/eYEBfg5a - SNNs can provide biological plausibility, ultra-low power consumption, diverse learning capabilities, and high accuracy for enabling robot intelligence. - Current SNN deployments in robotics focus on enhancing learning quality but give little attention to reliability, security, benchmarks, and development frameworks. - Key challenges are developing intelligence, energy efficiency, reliability, security, benchmarks, and end-to-end frameworks for neuromorphic robotics. - Perspectives include embodied intelligence, hardware/software optimizations, benchmarks, reliability, security, and synergistic development of energy-efficient and robust neuromorphic robotics. #AI #robotics #neuromorphiccomputing
Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack
arxiv.org
To view or add a comment, sign in
-
Co-Founder, Chief AI & Analytics Advisor @ InstaDataHelp | Innovator and Patent-Holder in Gen AI and LLM | Data Science Thought Leader and Blogger | FRSS(UK) FSASS FRIOASD | 16 Years of Excellence
The Rise of Cognitive Robotics: Merging Artificial Intelligence and Robotics The Rise of Cognitive Robotics: Merging Artificial Intelligence and Robotics Introduction: In recent years, the field of robotics has witnessed a significant transformation with the integration of artificial intelligence (AI) techniques. This convergence has given birth to a new era of robotics known as cognitive robotics. Cognitive robotics combines the power of AI algorithms with […] https://lnkd.in/dJDPMqnF
The Rise of Cognitive Robotics: Merging Artificial Intelligence and Robotics
To view or add a comment, sign in
-
Robotics researchers from around the globe will land in the City of Atlanta for the Conference on Robot Learning, Nov. 6 - 9, with Georgia Institute of Technology hosting. College of Computing researchers in the program will show (1) advancements in robots working with people and (2) how #AI is shaping robotics. Coffee-serving bots may or may not make an appearance... Explore: https://lnkd.in/dYUKA4n4
CoRL 2023
https://sites.gatech.edu/research
To view or add a comment, sign in
2,496 followers