Goto

Collaborating Authors

 Telecommunications


Cellular-Connected UAVs over 5G: Deep Reinforcement Learning for Interference Management

arXiv.org Artificial Intelligence

In this paper, an interference-aware path planning scheme for a network of cellular-connected unmanned aerial vehicles (UAVs) is proposed. In particular, each UAV aims at achieving a tradeoff between maximizing energy efficiency and minimizing both wireless latency and the interference level caused on the ground network along its path. The problem is cast as a dynamic game among UAVs. To solve this game, a deep reinforcement learning algorithm, based on echo state network (ESN) cells, is proposed. The introduced deep ESN architecture is trained to allow each UAV to map each observation of the network state to an action, with the goal of minimizing a sequence of time-dependent utility functions. Each UAV uses ESN to learn its optimal path, transmission power level, and cell association vector at different locations along its path. The proposed algorithm is shown to reach a subgame perfect Nash equilibrium (SPNE) upon convergence. Moreover, an upper and lower bound for the altitude of the UAVs is derived thus reducing the computational complexity of the proposed algorithm. Simulation results show that the proposed scheme achieves better wireless latency per UAV and rate per ground user (UE) while requiring a number of steps that is comparable to a heuristic baseline that considers moving via the shortest distance towards the corresponding destinations. The results also show that the optimal altitude of the UAVs varies based on the ground network density and the UE data rate requirements and plays a vital role in minimizing the interference level on the ground UEs as well as the wireless transmission delay of the UAV.


Blackberry and Qualcomm to partner on autonomous vehicle technology

#artificialintelligence

Leading Canadian technology firm Blackberry has announced the expansion of its ongoing partnership with Qualcomm that will see the two companies collaborating on the development of technology for autonomous vehicles. "BlackBerry and Qualcomm Technologies have had a long-standing relationship for over a decade, collaborating on technologies that have revolutionized the way people live and work," said Sandeep Chennakeshu, President of BlackBerry Technology Solutions. "Today's announcement elevates our relationship as we aim to accelerate the delivery of the next generation platforms that connected vehicles will rely upon." Blackberry will integrate its QNX software with Qualcomm's hardware platforms that will then be used in several applications including virtual cockpit controllers, cellular vehicle-to-everything (C-V2X) technology and infotainment systems. "As innovation in the automotive industry accelerates it becomes necessary for industry leaders to work together to deliver leading-edge technology platforms that help to make vehicles safer, more connected, and increasingly autonomous," said Patrick Little, Senior Vice President and General Manager of Automotive, Qualcomm Technologies.


Huawei upgrades its operating system with AI capabilities - ET Telecom

#artificialintelligence

NEW DELHI: Chinese handset maker Huawei on Friday unveiled EMUI 8.0 -- its custom Operating System (OS) based on Android Oreo platform that promises to boost productivity with Artificial Intelligence (AI) capabilities. The EMUI 8.0, already available on Honor View 10, will be rolled out on devices such as Honor 8 Pro, Honor 9i, Honor 7X and Honor 8 Lite soon. "The update significantly cuts down on the number of steps needed to achieve the desired function through its smart applications like navigation dock and smart screen. It enables the user to reach 90 per cent of the core functions in a single-click," Huawei said in a statement. The custom OS engages in low-memory management by allocating resources in a way to provide more space to ensure holistic experience coupled with AI capabilities.


Few Android Phones Will Try To Copy Apple's Face ID In Early 2018

International Business Times

With Apple deciding to use new Depth Sensing technology for the iPhone X's Face ID, many believe that Android phone makers might start using it for their own devices. However, it looks like many Android flagships coming out during the first half of 2018 won't have the same 3D-sensing feature. Industry sources say that smartphone vendors, particularly in China, are actually more interested in selling the rest of their unsold inventories. This is also the reason why many of those Android phone manufacturers are postponing plans to develop new technologies like fast charging, wireless charging and Face ID-like features, according to Digitimes. Another reason that's hindering the adoption of 3D-sensing cameras on Android smartphones is the slow yield rates for producing components.


Distributed Constraint Optimization Problems and Applications: A Survey

arXiv.org Artificial Intelligence

The field of Multi-Agent System (MAS) is an active area of research within Artificial Intelligence, with an increasingly important impact in industrial and other real-world applications. Within a MAS, autonomous agents interact to pursue personal interests and/or to achieve common objectives. Distributed Constraint Optimization Problems (DCOPs) have emerged as one of the prominent agent architectures to govern the agents' autonomous behavior, where both algorithms and communication models are driven by the structure of the specific problem. During the last decade, several extensions to the DCOP model have enabled them to support MAS in complex, real-time, and uncertain environments. This survey aims at providing an overview of the DCOP model, giving a classification of its multiple extensions and addressing both resolution methods and applications that find a natural mapping within each class of DCOPs. The proposed classification suggests several future perspectives for DCOP extensions, and identifies challenges in the design of efficient resolution algorithms, possibly through the adaptation of strategies from different areas.


Qualcomm promotes the concept of combining routers with smart speakers

PCWorld

Qualcomm executives called the new Asus Lyra Voice a model for routers going forward: partly a speaker, partly a router, and powered by Amazon's Alexa assistant. The company said it's trying to convince ISPs like Cox and Comcast to move in that direction. Unlike AMD and Intel, you can't buy Qualcomm chips to build your own smartphones and routers. But when company executives take the stage at CES to describe how future products should look, it's worth paying attention. Qualcomm announced three versions of its Smart Audio Platform--complete with a quad-core ARM A53 processor, audio DSP, 802.11ac


Qualcomm is making Cortana smart speakers easier to build

Engadget

Alexa and Google Assistant are appearing on what seems like every single gadget at CES 2018, but Cortana's absence from the party has made it the butt of jokes. Luckily, Qualcomm has announced that it's Smart Audio Platform, which includes microphone, speaker and voice recognition tech, now supports Cortana. That will make it a lot easier for smart speaker manufacturers to build devices around the neglected bot, instead of Google and Amazon's more popular platforms. Microsoft's Cortana has recently landed on Harmon Kardon's Invoke speakers (below) and its own Cortana thermostat. Apart from those wins, however, it's getting badly beaten in its race with Amazon and Google to get voice AI onto gadgets.


Longer Battery Life For Wireless Earbuds A Possibility With Qualcomm's New Chip

International Business Times

Qualcomm has announced a new chipset that the company claims will vastly improve wireless earbuds and solve the device's biggest problem. Called the QCC5100, the new Qualcomm SoC (system-on-chip) will be able to deliver three times the battery life of future wireless earbuds. "This breakthrough single-chip solution is designed to dramatically reduce power consumption and offers enhanced processing capabilities to help our customers build new life-enhancing, feature-rich devices," Qualcomm senior vice president Anthony Murray said. "This will open new possibilities for extended-use hearable applications including virtual assistants, augmented hearing and enhanced listening" The Qualcomm QCC5100 series chipset will be made available to makers of truly wireless earbuds soon. It comes with its own dedicated application processor sub-system, dual DSP architecture and next-gen ADK software.


Qualcomm's Home Hub platform will bring Google Assistant to more people

#artificialintelligence

The Internet of Things is going to get noisier. Qualcomm is launching its Home Hub platform with support for Android Things and Google Assistant. At CES 2018, the big tech trade show in Las Vegas, Qualcomm unveiled its purpose-built platforms and system modules for home devices that are enabled with the artificial intelligence of Google Assistant. The Home Hub platform is based on the Qualcomm SDA624 and SDA212 system on chips (SoCs). The idea is to make it easy for Qualcomm's customers to create devices for the Internet of Things, which makes everyday objects smart and connected.


Google Assistant is coming to headphones from JBL, LG, and Sony

#artificialintelligence

As part of a series of news announced today by Google, wireless headphones made to work especially with Google Assistant are on the way from brands like JBL, Sony, and LG. Up until today, some of the only headphones optimized for Google Assistant were the Bose QuietComfort 35 II and Pixel Buds, Google's first-ever wireless headphones. Also announced today: Google Assistant is coming to a series of new smart speakers -- including some with visual touchscreen displays -- and Google Assistant will become the assistant for Android Auto. Google Assistant can be accessed through any pair of wired or wireless headphones connected to an Android device, but headphones with this kind of integration allow access the AI assistant without the need to open your phone. With the touch of a button on the side of the headphones, you can speak directly with Google Assistant to do things like create calendar events, make phone calls, and receive auditory push notifications.