Found in Robotics News & Content, with a score of 8.33
October 23, 2021
…told Robotics 24/7. “Then they worked on racing strategies, perception, and passing algorithms. Nobody should be competing on how to get a camera to work or worrying if drive by wire is flaky. All the cars can do a yellow-flag lap without human intervention.” “The teams can figure out their kinematics models and decisioning based on perception,” Speed said. “I'd be remiss if I didn't say we did a lot of work with ADLINK commercial products as well. We've built the world's most powerful ROS 2 controller.” Open-source community supports IAC ADLINK has also partnered with The Autoware Foundation, the…
Found in Robotics News & Content, with a score of 12.12
October 21, 2021
…NVIDIA Corp. announced its latest efforts to deliver performant perception technologies to the Robot Operating System developer community. The Santa Clara, Calif.-based company said these initiatives will accelerate product development, improve performance, and simplify the task of incorporating computer vision and artificial intelligence functionality into ROS-based applications. NVIDIA claimed that it will provide the highest-performing, real-time stereo odometry system as a ROS package. The Santa Clara, Calif.-based company also noted that all NVIDIA inference deep neural networks (DNNs) will be available on NVIDIA GPU Cloud (NGC) as a ROS package with examples for image segmentation and pose estimation. In addition,…
Found in Robotics News & Content, with a score of 10.71
October 12, 2021
…Sarcos has partnered with BEA Systems PLC to develop perception for the U.S. Air Force. It also recently agreed to a merger with special-purpose acquisition company (SPAC) Rotor Acquisition Corp. and began trading on the New York Stock Exchange. Sarcos Guardian DX is the defense variant of its XT The Guardian DX robot is the defense-specific variant of the Guardian XT. The highly dexterous mobile robot is itself is a variant of the award-winning Sarcos Guardian XO full-body, battery-powered industrial exoskeleton. The Guardian DX robot is a teleoperated, dual-armed robot designed to perform tasks with human-like dexterity while keeping the…
Found in Robotics News & Content, with a score of 7.85
October 11, 2021
…research advances understanding across various tasks crucial for robotic perception, including semantic segmentation, 3D object detection, and multi-object tracking, said Toyota. Over the past six years, the Toyota Research Intitute (TRI) said its researchers have made significant strides in robotics, automated driving, and materials science in large part due to machine learning—the application of computer algorithms that constantly improve with experience and data. “Machine learning is the foundation of our research,” stated Dr. Gill Pratt, CEO of TRI. “We are working to create scientific breakthroughs in the discipline of machine learning itself and then apply those breakthroughs to accelerate discoveries…
Found in Robotics News & Content, with a score of 17.29
October 08, 2021
…detection and ranging platform with Seoul Robotics' SENSR 3D perception software. The companies said they will provide a complete system for long-range object detection, classification, and perception for intelligent traffic systems (ITS) by providing 3D perception for vehicles, cyclists, and pedestrians at distances beyond 300 m (984.2 ft.). “ITS integrators typically don’t source individual sensors and software, instead relying on complete solution providers for smart mobility, traffic management, and automated tolling applications, and that’s exactly what we’re delivering,” said Akram Benmbarek, vice president of business development and strategic initiatives at AEye. “With the integration of the 4Sight M and SENSR,…
Found in Robotics News & Content, with a score of 7.83
October 07, 2021
…system “is the first radar that can truly enrich perception algorithms, making sure they operate in all possible driving scenarios.” The company said it provides capabilities that were previously associated with more costly sensors like lidar. In April, China-based AutoX chose Arbe to supply radar for its Level 4 robotaxis. Arbe to receive $118M in SPAC deal Industrial Tech Acquisitions (ITAC) shareholders approved the business combination with Arbe at a special meeting on Oct. 5. The SPAC is sponsored by Texas Ventures. “I am excited to complete this deal and look forward to working with the entire Arbe team as…
Found in Robotics News & Content, with a score of 9.64
October 05, 2021
…proposition. How can you gain confidence that the robot’s perception capabilities are robust enough so it performs safely and as planned? Trimble faced this challenge when it started building plans to deploy the Spot robot in a variety of indoor settings and construction environments. Sunnyvale, Calif.-based Trimble needed to tune the machine learning (ML) models to the exact indoor environments so Boston Dynamics' quadruped could autonomously operate in these different indoor settings. “As we deploy Spot equipped with our data-collection sensors and field-control software to indoor environments, we need to develop a cost effective and reliable workflow to train our…
Found in Robotics News & Content, with a score of 4.53
October 04, 2021
…to scale quickly, safely, and efficiently. The Kodiak Vision perception system considers every sensor—including lidar, cameras, and radar—primary, said the company. Kodiak Vision fuses data from the sensors and considers the relative strengths and weaknesses of each type. This incorporates extra redundancies and cross-validates data, adding another layer of safety to the self-driving system, Kodiak said. In addition, the truck incorporates the ZF Full Range Radar and Luminar's long-range Iris lidar for performance and reliability. The company said these sensors, combined with its previously announced integration with Hesai Technnology Co. 360-degree scanning lidar for side- and rear-view detection, will provide…
Found in Robotics News & Content, with a score of 10.65
October 01, 2021
…includes a robotic arm guided by advanced vision and perception technologies, enabling cases to be picked from a single- or mixed-SKU pallet on a fixed or mobile location. The computer vision technology identifies the exact location of every case on the pallet, while perception software automatically recognizes a wide variety of packaging to allow for seamless handling of a continuous flow of pallets in any sequence without requiring any pre-programming or operator intervention. The advanced machine learning and motion planning optimizes the movements of the robotic arm to ensure maximum picking speed and efficiency. The control logic also senses the…
Found in Robotics News & Content, with a score of 4.66
September 30, 2021
…systems [ADAS],” he explained. “Not only are we providing perception to cars or robots, but these systems are also helping people drive more safely with features such as lanekeeping. That's where we're focused.” Activ Surgical's hardware-agnostic ActivInsights software is intended to combine augmented reality (AR), machine learning, and robotics for autonomous and collaborative surgery. “We're working with a number of robotics vendors to make their systems better,” said Kim. “With a realtime flow of information and optical signatures, the surgeon can identify different types of tissue.” “ActiveSight is a simple module between any camera and endoscope system, allowing it to…
Found in Robotics News & Content, with a score of 5.41
September 27, 2021
…flying, while simultaneously addressing in a unified manner the perception and navigation challenges.” “In the underground environment, there are so many challenges from lighting and communications to the slipperiness of terrain itself,” said Dr. Marco Camurri, a senior researcher at Oxford University. “This demanded a whole range of breakthroughs by our team.” Virtual Competition tested simulated exploration Teams in the Virtual Competition developed software and algorithms using virtual models of systems, environments, and terrain to compete in simulation-based events and explore simulated environments. The teams also used virtual drones and mobile robots to find artifacts hidden in the different environments…
Found in Robotics News & Content, with a score of 10.96
September 24, 2021
…labor shortages. Driven by machine learning and advances in perception and gripping technologies, Honeywell said its Smart Flexible Depalletizer minimizes the need for human workers to break down pallet loads. Such roles are at risk for safety incidents, experience high turnover, and are currently difficult to fill. A typical midsize to large distribution center unpacks up to several thousand pallets per day, with the probability of errors, worker fatigue, and injury increasing during each shift, noted the company. “Even when manual operations are running smoothly without injuries, the physical, repetitive task of unloading pallets is variable and limited by human…
