Researchers from NVIDIA, led by Stan Birchfield and Jonathan Tremblay, developed a first of its kind deep learning-based system that can teach a robot to complete a task by just observing the actions of a human. The method is designed to enhance communication between humans and robots and at the same time further research that will enable people to work alongside robots seamlessly.
“For robots to perform useful tasks in real-world settings, it must be easy to communicate the task to the robot; this includes both the desired result and any hints as to the best means to achieve that result,” the researchers stated in their research paper. “With demonstrations, a user can communicate a task to the robot and provide clues as to how to best perform the task.”
Using NVIDIA TITAN X GPUs, the researchers trained a sequence of neural networks to perform duties associated with perception, program generation, and program execution. As a result, the robot was able to learn a task from a single demonstration in the real world.
Once the robot sees a task, it generates a human-readable description of the steps necessary to re-perform the task. The description allows the user to quickly identify and correct any issues with the robot’s interpretation of the human demonstration before execution on the real robot.
The key to achieving this capability is leveraging the power of synthetic data to train the neural networks. Current approaches to training neural networks require large amounts of labeled training data, which is a serious bottleneck in these systems. With synthetic data generation, an almost infinite amount of labeled training data can be produced with very little effort.
This is also the first time an image-centric domain randomization approach has been used on a robot. Domain randomization is a technique to produce synthetic data with large amounts of diversity, which then fools the perception network into seeing the real-world data as simply another variation of its training data. The researchers chose to process the data in an image-centric manner to ensure that the networks are not dependent on the camera or environment.
“The perception network as described applies to any rigid real-world object that can be reasonably approximated by its 3D bounding cuboid,” the researchers said. “Despite never observing a real image during training, the perception network reliably detects the bounding cuboids of objects in real images, even under severe occlusions.”
For their demonstration, the team trained object detectors on several colored blocks and a toy car. The system was taught the physical relationship of blocks, whether they are stacked on top of one another or placed next to each other.
In the video above, the human operator shows a pair of stacks of cubes to the robot. The system then infers an appropriate program and correctly places the cubes in the correct order. Because it takes the current state of the world into account during execution, the system is able to recover from mistakes in real time.
The researchers will present their research paper and work at the International Conference on Robotics and Automation (ICRA), in Brisbane, Australia this week.
The team says they will continue to explore the use of synthetic training data for robotics manipulation to extend the capabilities of their method to additional scenarios.
via NVIDIA: Read the research paper
The Latest on: Robot learning
via Google News
The Latest on: Robot learning
- Programmable Robots Market Size to surge at 14.9% CAGR and Hit 6297 million USD by 2027on March 4, 2021 at 2:14 am
Selbyville, Delaware Global Programmable Robots Market Report added at Market Study Report LLC offers industry ...
- Cognex and the Rise of the Roboton March 4, 2021 at 2:12 am
Companies have been transitioning their manufacturing jobs to machines for years, but we’re about to see it on a much broader scale, forecasts Sean Brodrick, a leading growth stock expert and editor ...
- Amazon launches reinforcement learning tools to manage robots’ workflowson March 3, 2021 at 9:25 pm
Kubeflow Components, a toolkit supporting the company’s AWS RoboMaker service for orchestrating robotics workflows. Amazon says that the goal is to make it faster to experiment and manage robotics ...
- Mill Valley Library Catapults Robotics Learning Program For Kidson March 3, 2021 at 3:29 pm
The Mill Valley Public Library is launching a robotics learning program for children. The virtual program, which is open to fourth through seventh graders, aims to teach physics and mechanical ...
- Researchers’ Robots Designed To Avoid Environmental Dangers, Deliver Data Quicklyon March 3, 2021 at 3:10 pm
Dr. David Lary and his group’s autonomous devices may be ideally suited for hazardous environmental situations and holistic environmental surveys of ecosystems.
- Asensus Surgical scores general surgery clearance for its Senhance roboton March 3, 2021 at 8:00 am
Its Senhance laparoscopic system provides eye-tracking camera controls, haptic feedback and 3D visualization, paired with instruments as small as 3 millimeters.
- Unity Releases Enhancements for Robotics Industryon March 2, 2021 at 9:30 pm
Unity, the world’s leading platform for creating and operating real-time 3D (RT3D) content, today released its Object Pose Estimation demonstration, which combines the power of computer vision and ...
- Programmable Robots Market | Share, Growth Rate, Opportunities and Market Forecast 2027on March 2, 2021 at 6:03 am
Global Programmable Robots Market is valued at approximately USD 2073 million in 2019 and is anticipated to grow with ...
- Worldwide security robot market size to boom at 8% CAGR through 2027on March 2, 2021 at 2:43 am
The business intelligence report on ‘Global Security Robot Market’ provides valuable insights pertaining to growth catalysts and profitable opportunities dormant in the industry space, while ...
via Bing News