The motion planning problem involves finding a collision-free path from a robot's starting to its target configuration. Recently, self-supervised learning methods have emerged to tackle motion planning problems without requiring expensive expert demonstrations. They solve the Eikonal equation for training neural networks and lead to efficient solutions. However, these methods struggle in complex environments because they fail to maintain key properties of the Eikonal equation, such as optimal value functions and geodesic distances. To overcome these limitations, we propose a novel self-supervised temporal difference metric learning approach that solves the Eikonal equation more accurately and enhances performance in solving complex and unseen planning tasks. Our method enforces Bellman's principle of optimality over finite regions, using temporal difference learning to avoid spurious local minima while incorporating metric learning to preserve the Eikonal equation's essential geodesic properties. We demonstrate that our approach significantly outperforms existing self-supervised learning methods in handling complex environments and generalizing to unseen environments, with robot configurations ranging from 2 to 12 degrees of freedom (DOF).

An artificial intelligence (AI) tool developed by Cedars-Sinai investigators accurately predicted who would develop pancreatic cancer based on what their CT scan images looked like years prior to being diagnosed with the disease. The findings, which may help prevent death through early detection of one of the most challenging cancers to treat, are published in the journal Cancer Biomarkers. "This AI tool was able to capture and quantify very subtle, early signs of pancreatic ductal adenocarcinoma in CT scans years before occurrence of the disease. These are signs that the human eye would never be able to discern," said Debiao Li, PhD, director of the Biomedical Imaging Research Institute, professor of Biomedical Sciences and Imaging at Cedars-Sinai, and senior and corresponding author of the study. Li is also the Karl Storz Chair in Minimally Invasive Surgery in Honor of George Berci, MD.

BARCELONA, June 28 (Reuters) - Verizon (VZ.N) on Monday showcased two robots on the stage of the Mobile World conference, saying that bots use 5G connectivity and mobile edge computing to communicate with each other. Edge computing uses augmented reality and machine learning to analyse bulk data where it was gathered - whether factory floor, oil rig or office space - and requires fast data transfers of the kind that only high-speed 5G signals provide. "When you have more than one robot on the floor, you run into a problem, as these are still just machines, and they can't naturally communicate with one another," Verizon's Chief Strategy Officer Rima Qureshi said at the event in Barcelona. "5G will make it possible for robots to connect with other robots and devices of all kinds in a way that simply wasn't possible before," she said. Connected, smarter robots are considered crucial to making areas such as factory floors more efficient through automation, with remote monitoring cutting costs and the need for plant infrastructure.

As Verizon Communications Inc. rolls out 5G service, Rima Qureshi has a clear mission: find ways to move beyond providing basic connectivity. Ms. Qureshi, Verizon's chief strategy officer, leads a team charged with being "as creative and off the wall as possible" while remaining dead set on creating products that can be monetized, she says. "I don't want you to come up with demos, I want products," she tells them, grilling members monthly on the financial viability of products and services. That drive has meant forming new partnerships with technology giants including Amazon.com Inc. and Microsoft Corp.; creating new business-use cases for connected products like robots and drones; and finding revenue models that take advantage of features of 5G. Those include ultra low latency, or the much shorter time it takes for machines to respond to each other over a network, and high throughput, or the ability to move massive amounts of data at speeds far beyond those possible with 4G.