- 16 May 2018 12:27
NVIDIA Brings the Brains Behind the Bots to Brisbane for ICRA
NVIDIA is bringing its researchers — the brains behind its bots — to the International Conference on Robotics and Automation (ICRA) in Brisbane, Australia, from May 21 to 25.
Claire Delaunay, vice president of engineering and robotics, and Dieter Fox, senior director of robotics research, will lead a team at ICRA, a premier forum held annually since 1984 for robotics researchers from across the globe. Around 2,500 participants from around 60 countries are expected at this year’s event.
For more than a decade, Delaunay has led robotics teams at startups, research labs and companies, including Google, where she was the programme lead. Most recently she co-founded Otto, which was acquired by Uber, where she served as the director of engineering before coming to NVIDIA to develop robotic solutions.
Fox joined NVIDIA to head the robotics research lab in Seattle. The goal of the lab is to develop the next generation of robots that can robustly manipulate the physical world and interact with people naturally. He also runs the University of Washington Robotics and State Estimation Lab, where his research focuses on robotics with strong connections to AI, computer vision and machine learning.
ICRA presents a great opportunity to meet the NVIDIA team, go in-depth with recent work shaping robotics research and development, and learn how NVIDIA GPUs and AI are powering the biggest advancements in autonomous machines.
NVIDIA Research will be conducting talks on: • Re3: Real-Time Recurrent Regression Networks for Visual Tracking of Generic Objects – Robust object tracking requires knowledge and understanding of the object being tracked: its appearance, its motion and how it changes over time. A tracker must be able to modify its underlying model and adapt to new observations. Re3 is a real-time deep object tracker capable of incorporating temporal information into its model. • SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control – This talk describes an approach to deep visuomotor control using structured deep dynamics models. NVIDIA’s deep dynamics model, a variant of SE3-Nets, learns a low-dimensional pose embedding for visuomotor control via an encoder-decoder structure. • Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations – This talk presents a system to infer and execute a human-readable program from a real-world demonstration. It consists of a series of neural networks to perform perception, program generation and program execution. The networks are trained entirely in simulation, and the system is tested in the real world on the pick-and-place problem of stacking colored cubes using a Baxter robot.
After the conference on Monday and Tuesday evenings, NVIDIA will host Jetson meetups at the iconic Fox Hotel. Delaunay, Fox and other NVIDIA researchers — along with NVIDIA developers and partners — will be on hand.
During the meetups, there will be special pricing on the NVIDIA Jetson TX2 Developer Kit for AUD599, including delivery.
NVIDIA is sponsoring the ICRA 2018 DJI RoboMaster AI Challenge, in which robots drive and launch projectiles using AI technologies. Each team is required to build up to two autonomous robots to compete in an obstacle-filled arena. Fourteen of the 22 competitors leverage the NVIDIA Jetson platform to power, control, navigate, perceive and execute autonomous functions. Winning teams will be awarded an NVIDIA TITAN or Jetson TX2.
Those keen on careers at NVIDIA can stop by ICRA stands 7 and 8 at the Brisbane Convention and Exhibition Centre to speak with the NVIDIA recruiting team.