Found in Robotics White Papers & Archives, with a score of 27.47
September 25, 2024
…at their fingertips better than ever before. With robotics and automation generating mountains of valuable data for humans and neural networks to sift through, organizations can accurately monitor and track their inventory and workflows. When combined with generative AI analytics, robots can serve as mobile data platforms, informing decision-making and improving operational efficiency for commercial and industrial end users. In this Special Focus Issue Dexory delivers real-time visibility for warehouse operators Nokia AIMS automates inventory monitoring with AI-enabled drones ProGlove wearable scanners MARK the spot in the warehouse Brain Corp's Sense Suite helps address retail inventory challenges ...And more
Found in Robotics News & Content, with a score of 10.02
August 19, 2024
…automated lift trucks require. So rather than treating its neural network as a black box and accepting the output as truth, Seegrid is applying a hybrid-AI approach. It validates the output of the neural network using classical computer vision techniques in real-time. “We're solving industrial problems with the data sets we have,” Panzarella said, noting that the AI and data sets Seegrid is using are different from the massive, generalized AI models described in popular media. “Industrial use-cases typically are not afforded access to internet-scale data. Relatively speaking, we are dealing with small data.” Data sharing to demonstrate what’s possible…
Found in Robotics News & Content, with a score of 46.49
August 08, 2024
…in 2024, valuing the company at $2.6 billion. OpenAI neural network improvements in Figure 02 As part of the new humanoid, Figure 02 has a new addition for its artificial intelligence and neural network technology for, “speech-to-speech reasoning,” according to the company. When Figure AI announced its Series B round, including in the investors were OpenAI, Microsoft, NVIDIA and others. Along with the funding, OpenAI and Figure AI announced the companies had reached a collaboration agreement to develop AI models. The research combines OpenAI’s neural network and artificial intelligence with Figure’s humanoid hardware and software. Figure 02, according to the…
Found in Robotics News & Content, with a score of 12.53
May 12, 2024
…the ideal balance between computational speed and accuracy. The neural network autonomously recognizes the surfaces from which an object can be picked, using a suction cup to facilitate identification of the most suitable grasping points. As a result, MI.RA/OnePicker can achieve path planning and collision-free movements safely while ensuring optimal piece picking performance by the robot, Comau said. The vision-based piece picking system can autonomously grasp randomly-placed heterogeneous objects As an all-in-one-system, MI.RA/OnePicker comes with Comau’s Racer5 cobot, a six-axis articulated robot that the company said can deliver speed, accuracy, repeatability, and certified fenceless collaboration safety without cages. The compact…
Found in Robotics News & Content, with a score of 14.00
May 06, 2024
…on a transformer deep learning architecture that allows a neural network to learn by tracking relationships in data. They’re generally trained on huge datasets and can be used to process and understand sensor and robot information as magically as ChatGPT for text. This enables robot perception and decision-making like never before and provides zero-shot learning - the ability to perform tasks without prior examples. NVIDIA’s collaboration with Intrinsic, a robotics software and AI company, demonstrates the potential for a universally applicable robotic-grasping skill to work across grippers, environments and objects. “For the broader industry, our work with NVIDIA shows how…
Found in Robotics News & Content, with a score of 12.82
October 30, 2023
…It describes the DeepSeeColor model, which uses two convolutional neural networks to reduce backscatter and correct colors in real time on the NVIDIA Jetson Orin NX while undersea. “NVIDIA GPUs are involved in a large portion of our pipeline because, basically, when the images come in, we use DeepSeeColor to color correct them, and then we can do the fish detection and transmit that to a scientist up at the surface on a boat,” said Stewart Jamieson, a robotics Ph.D. candidate at MIT and an AI developer at WARPLab. CUREE cameras detect fish and reefs CUREE includes four forward-facing cameras,…
Found in Robotics News & Content, with a score of 8.02
October 18, 2023
…models created with generative AI can outperform traditional convolutional neural network (CNN)-based models, NVIDIA noted. “Legacy CNNs are rigid and rule-based and require lots of labeled data, slowing the development cycle,” said Talla. “Generative AI is generalizable and with natural-language prompts, anyone can get the right output.” Generative AI could add $10.5 billion in revenue for manufacturing operations worldwide by 2033, predicted ABI Research. “Generative AI will significantly accelerate deployments of AI at the edge with better generalization, ease of use, and higher accuracy than previously possible,” Talla said. “This largest-ever software expansion of our Metropolis and Isaac frameworks on…
Found in Robotics News & Content, with a score of 12.30
October 13, 2023
…physics principles rather than taking noisy data. Our deep neural networks use insect-like vision to create structured 3D geometry. We're looking for AI intelligent animals versus Web-based robotics.” Electric Sheep grows through acquisition The acquisitions of Phenix Landscape and Complete Landscape will help Electric Sheep to grow eightfold, predicted the company. It plans to offer full services including data collection rather than just robotics as a service (RaaS), asserted Murthy. “This gets to the heart of why we chose this business model,” he told Robotics 24/7. “There's an inability to unlock value from progressive automation, which is held to extremely…
Found in Robotics News & Content, with a score of 19.01
August 03, 2023
…of Slamcore, in a release. “We provide a reference neural network for identifying objects but have designed this feature with flexibility in mind. Customers can use our API to integrate their own networks and start to truly harness the power of semantic classification in 3D space.” Perceive now widely available The Perceive functions were previously available only through direct customer engagements with Slamcore. As a standard art of the SDK, they “allow many more developers to quickly add the power of semantic segmentation to their products,” said the company. Slamcore explained that Perceive builds on Position and Mapping functions to…
Found in Robotics News & Content, with a score of 7.86
July 30, 2023
…does PIGINet avoid those predefined rules? PIGINet is a neural network that takes in “Plans, Images, Goal, and Initial facts,” then predicts the probability that a task plan can be refined to find feasible motion plans. In simple terms, it employs a transformer encoder, a versatile and state-of-the-art model designed to operate on data sequences. The input sequence, in this case, is information about which task plan it is considering, images of the environment, and symbolic encodings of the initial state and the desired goal. The encoder combines the task plans, image, and text to generate a prediction regarding the…
Found in Robotics News & Content, with a score of 8.89
July 16, 2023
…Transformer for 3D Object Manipulation uses a type of neural network called a multi-view transformer to produce virtual views from the camera input. The work combines text prompts, video input and simulation to achieve 36x faster training time than the current state of the art — reducing the time needed to teach the robot from weeks to days—with a 26% improvement in the robot’s task success rate. Robots hands are grasping dexterity Researchers have taken on the challenge of creating more agile hands that can work in all kinds of settings and take on new tasks. Developers are building robotic…
Found in Robotics News & Content, with a score of 9.84
July 13, 2023
…our AMRs sense other robots or humans, but the neural network can also understand doors. If an AMR sees a lift truck, it knows when to stop. Our robot-agnostic fleet manager integrates with WMS and TMS [transportation management systems] if customers have one, and they help us to dispatch orders of higher or lower priority. Our fleet manager collaborates with human pickers and works like Uber—it tells pickers where to go next through PDAs [personal digital assistants]. How much localization have you had to do coming to the U.S. or Australia and New Zealand? Guan: We found it interesting. In…
