Published
In this work, researchers from NVIDIA, Georgia Institute of Technology, and the University of Washington, developed a new motion generation and control framework that enables globally stable controller design within intrinsically non-Euclidean spaces.
Non-Euclidean geometries are not often modeled explicitly in robotics, but are nonetheless common in the natural world. One important example is the apparent non-Euclidean behavior of obstacle avoidance. Obstacles become holes in this setting. As a result, straight lines are no longer a reasonable definition of shortest distance—geodesics must, therefore, naturally flow around them. This behavior implies a form of non-Euclidean geometry: the space is naturally curved by the presence of obstacles.
Learn more: https://arxiv.org/pdf/1811.07049.pdf
Non-Euclidean geometries are not often modeled explicitly in robotics, but are nonetheless common in the natural world. One important example is the apparent non-Euclidean behavior of obstacle avoidance. Obstacles become holes in this setting. As a result, straight lines are no longer a reasonable definition of shortest distance—geodesics must, therefore, naturally flow around them. This behavior implies a form of non-Euclidean geometry: the space is naturally curved by the presence of obstacles.
Learn more: https://arxiv.org/pdf/1811.07049.pdf
- Category
- Hardware
Sign in or sign up to post comments.
Be the first to comment
Up Next
-
01:10
Research at NVIDIA: GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning
-
02:15
Research at NVIDIA: AI Reconstructs Photos with Realistic Results
-
00:47
Research at NVIDIA: Medical Image Synthesis for Data Augmentation and Anonymization Using GANs
-
02:11
NVIDIA Research: First Privacy-Preserving Federated Learning System for Medical Imaging
-
01:39
How NVIDIA Research is Teaching Robots to Interact with Humans
-
01:43
Research at NVIDIA: 3D MRI Brain Tumor Segmentation Using Autoencoder Regularization
-
01:20
NVIDIA Graphics Research
-
01:34
Accelerating Deep Learning Research with NVIDIA DGX Station A100
-
02:18
All the Feels: NVIDIA Shares Expressive Speech Synthesis Research at Interspeech
-
1:57:59
GTC China 2020 Keynote Spotlights NVIDIA Technology and Research
-
01:41
NVIDIA Research Achieves AI Training Breakthrough Using Limited Datasets
-
02:40
Research at NVIDIA: New Core AI and Machine Learning Lab
-
06:49
NVIDIA GTC 2021 Keynote Part 4: DGX - The Essential Instrument for AI Research
-
02:40
Robotics Research at NVIDIA: Closing the Sim-to-Real Loop
-
01:39
Research at NVIDIA: Improving Landmark Localization with a New Deep Learning Architecture
-
01:55
Trail Blazing our Future with AI and NVIDIA Research
-
01:33
Research at NVIDIA: The First Interactive AI Rendered Virtual World
-
02:10
NVIDIA Studio | Create Stunning Motion Graphics and VFX in Adobe After Effects With NVIDIA RTX
-
02:29
Research at NVIDIA: Structured Domain Randomization
-
01:28
Research at NVIDIA: Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects
-
02:01
Accelerating AI for Biomedical Research with The Broad Institute and NVIDIA
-
02:27
Celebrating Robotics in Seattle: NVIDIA Opens New AI Research Lab
Loading...