Related projects

Artificial intelligence training in space

Large-scale deployments of low Earth orbit satellites collect massive amount of Earth imageries and sensor data, but it is increasingly infeasible to download all the high-resolution images and train the corresponding AI models on the ground. In this project, we focus on novel distributed and federated learning frameworks (opens in new tab) that enables ground stations and satellites collaboratively train AI models without downloading all the data to the ground.

Related vertical(s): Edge computing

Cloudification of network stack for IoT in space

The “new space” revolution is bringing about a new era of innovation and possibility in the industry as private companies are pushing the boundaries of what is possible by launching thousands of Low Earth Orbit (LEO) satellites. One of the most exciting developments is the use of small IoT picosatellites (picosats) that envisions offering a cost-effective way to connect millions of IoT devices around the world that may not have access to terrestrial networks. The small size and low-complexity hardware of these satellites make them easy to build and launch into orbit, resulting in rapid scaling of IoT picosat networks. As picosat constellations scale, their traditional networking stack becomes the bottleneck because it does not incorporate constraints specific to picosat constellations. In this project, we innovate a new end-to-end networking stack for IoT in space by introducing cloudification of the network stack.

Related vertical(s): IoT

Leveraging AI for Pruning Control Overhead in 5G/6G

Networks In this project, we are leveraging AI and data driven tools to develop technologies that can help reduce the control overheads in 5G and future 6G cellular networks. The project tackles both header information encoded in data packets at different layers of the network stack, as well as control messages that are exchanged between the user device and the cellular RAN and core to manage functions like device registration and handoffs. Traditional network protocol design has maintained a logical separation between the user plane and the control plane. However, this project aims to break this separation and leverages correlated traffic and user patterns from the data plane to implicitly infer control plane events without the need to explicitly transmit control messages on the network. This would help improve network performance in terms of throughput and latency and would allow us to handle control events like handoffs proactively rather than reactively.

Related vertical(s): none

The post 6G | Space: AI for networking appeared first on Microsoft Research.

Related projects

Artificial intelligence training in space

Large-scale deployments of low Earth orbit satellites collect massive amount of Earth imageries and sensor data, but it is increasingly infeasible to download all the high-resolution images and train the corresponding AI models on the ground. In this project, we focus on novel distributed and federated learning frameworks (opens in new tab) that enables ground stations and satellites collaboratively train AI models without downloading all the data to the ground.

Related vertical(s): Space connectivity

Context-aware compression of satellite imagery in space

Transmitting raw space imagery data to the ground for processing presents difficulties due to limited network bandwidth, resulting in data being captured in restricted modes and taking hours to days to downlink. To address this, compression right in space is a more promising approach to reduce the amount of data transmitted. However, current compression techniques treat all pixels as having equal weight, despite not all parts of an image being equally important. Our proposed solution, Earth+, is a smart filtering and compression method that is implemented directly on the satellite. Earth+ leverages the rich historical dataset on earth to intelligently select a reference image that best represents the near future and uploads it to the satellite. Utilizing lightweight context-aware cloud detection and diff-based comparison, Earth+ identifies only the changed areas and transmits them back to earth, thereby significantly reducing data transmission volume.

Related vertical(s): Space connectivity

Kodan: Edgifying satellite applications for on-board computation in space

The decreasing costs of deploying space vehicles to low-Earth orbit have led to the emergence of large constellations of satellites. However, the high speeds of the satellites, the large sizes of image data, and the short ground station contacts have created a challenge for data downlink. Orbital edge computing (OEC) can filter data at the space edge and address the downlink bottleneck, but it shifts the challenge to the limited computation capacity onboard satellites. We present Kodan, an OEC system designed to maximize the utility of saturated satellite downlinks while mitigating the constraints of the computational bottleneck. Kodan has two phases: a one-time transformation step that uses a reference implementation of a satellite data analysis app, along with a representative dataset, to produce a set of specialized ML models targeted for deployment to the space edge. After deployment to a target satellite, a runtime system dynamically selects the best specialized model for each data sample to maximize valuable data downlinked within the constraints of the computational bottleneck.

Related vertical(s): Space connectivity

The post 6G | Space: Edge computing appeared first on Microsoft Research.

Related projects

Cloudification of network stack for IoT in space

The “new space” revolution is bringing about a new era of innovation and possibility in the industry as private companies are pushing the boundaries of what is possible by launching thousands of Low Earth Orbit (LEO) satellites. One of the most exciting developments is the use of small IoT picosatellites (picosats) that envisions offering a cost-effective way to connect millions of IoT devices around the world that may not have access to terrestrial networks. The small size and low-complexity hardware of these satellites make them easy to build and launch into orbit, resulting in rapid scaling of IoT picosat networks. As picosat constellations scale, their traditional networking stack becomes the bottleneck because it does not incorporate constraints specific to picosat constellations. In this project, we innovate a new end-to-end networking stack for IoT in space by introducing cloudification of the network stack.

Related vertical(s): Space connectivity

Echo: Ultra low-power satellite communication

Project Echo is focused on developing ultra-low-power satellite communication to reliably connect devices in resource constrained environments. We believe that these new wireless communication techniques will lead to the next generation of IoT devices for applications ranging from smart agriculture to communication in space.

Related vertical(s): Ultra-low-power connectivity

FoodVibes: Wireless sensing and communication for food supply chain traceability

At Microsoft Research, we are working towards a fully digitized and connected supply chain for agriculture and food. With the growing human population, there is a need to responsibly and sustainably meet the global food demands. Towards this goal, FoodVibes identifies critical traceability points in the global Agri Food Industry that are responsible for inefficiency and applies technological innovation to address key challenges faced by the industry. By leveraging our research in wireless communication, battery-free and IoT sensing, we are establishing traceability for key metrics related to nutrition, sustainability, and quality of the food that nourishes the global population. Some of these key challenges being addressed include creating traceability from farm to fork, especially for bulk commodities like grain, tracking the produce environment during transport and storage with novel sensing infrastructure and a communication scheme to ensure global connectivity to support this supply chain.

Related vertical(s): Space connectivity | Ultra-low-power connectivity

IoT in TV White Space spectrum

The deployment of Internet of Things (IoT) networks has rapidly increased over recent years – to connect homes, cities, farms, and many other industries. Today, these networks rely on connectivity solutions, such as LoRaWAN, operating in the ISM bands. Our experience from deployments in multiple countries has shown that such networks are bottlenecked by range and bandwidth. Therefore, we propose a new connectivity solution operating in TV White Space (TVWS) spectrum, where narrowband devices configured for IoT can opportunistically transmit data, while protecting incumbents from receiving harmful interference.

Related vertical(s): New spectrum and sharing

Low latency distributed downlink for low Earth orbit satellites

Low Earth orbit (LEO) satellites for Earth observation and IoT have become very popular in recent years. The earth observation satellites collect hundreds of Gigabytes of imagery during their orbit. This data needs to be downloaded using ground stations on Earth. However, due to the low altitudes, the satellites move fast with respect to a ground station on Earth, and consequently, have a few minutes time window to download the data to a single station. Although an LEO IoT satellite aggregates comparatively much lower amount of data, it uses very low data rate link to download the data. It, in turn, has a very negative impact on the freshness of data and overall throughput of the satellite networks. We propose a geographically distributed ground station design, DGS that improves robustness and reduces downlink latency. DGS is the first system to use a hybrid ground station model, where only a subset of ground stations are uplink-capable.

Related vertical(s): Space connectivity

SatSense: Sensing the Environment using Satellites

Project SatSense is focused on using satellite telemetry to develop new techniques for environmental monitoring. We believe this will lead to gaining accurate insights about today’s ecosystem at large-scale including forestry, agriculture, oil & gas, among others.

Related vertical(s): Ultra-low-power connectivity

Spectrum sharing between satellite and terrestrial networks

In a world where space and terrestrial networks are expanding at an unprecedented pace, it is critical to ensure that the radio spectrum, a finite resource, is utilized to benefit both types of networks. To achieve this, it is essential to have an inclusive spectrum management technology that can facilitate efficient spectrum sharing. We introduce our innovative solutions that enable spectrum sharing in two ways. Firstly, our cutting-edge NextG AI-driven spectrum database creates a new spectrum awareness service that ensures effective management of the spectrum. Secondly, our spectrum exploitation techniques leverage satellite artifacts that embed unique attributes in the RF signal transmitted from each satellite, enabling coexistence with other networks. Our innovations have been tested and evaluated in a real-world satellite network, providing compelling evidence of their efficacy. With these groundbreaking solutions, we are confident that we can overcome the challenges of managing the radio spectrum and drive forward a new era of progress and innovation in both terrestrial and space networks.

Related vertical(s): Space connectivity | New spectrum and sharing

The post 6G | Space: Internet of things (IoT) appeared first on Microsoft Research.

Related projects

IoT in TV White Space spectrum

The deployment of Internet of Things (IoT) networks has rapidly increased over recent years – to connect homes, cities, farms, and many other industries. Today, these networks rely on connectivity solutions, such as LoRaWAN, operating in the ISM bands. Our experience from deployments in multiple countries has shown that such networks are bottlenecked by range and bandwidth. Therefore, we propose a new connectivity solution operating in TV White Space (TVWS) spectrum, where narrowband devices configured for IoT can opportunistically transmit data, while protecting incumbents from receiving harmful interference.

Related vertical(s): IoT

Smart Surface

We explore the connections between reflective / metamaterial surfaces and next-generation wireless networks. 6G wireless network promises much faster and better wireless connectivity to cover residential, commercial, and industrial environments, as it uses larger bandwidth and higher wireless frequencies, e.g., mmWave, cmWave, and terahertz. However, the propagation of these high frequency wireless signals is heavily subject to the environment. The distribution of wireless signal strength is random and uneven across the covered area due to the ambient reflectors, blockage, and moving objects like human body. Thus, maintaining a consistent high throughput broadband wireless channel between the user and the access point is challenging. We ask – “Can we establish consistent high-throughput connections for terahertz and cmWave communication in a low-cost and scalable way?” Stay tuned.

Related vertical(s): Smart surfaces

Spectrum sharing between satellite and terrestrial networks

In a world where space and terrestrial networks are expanding at an unprecedented pace, it is critical to ensure that the radio spectrum, a finite resource, is utilized to benefit both types of networks. To achieve this, it is essential to have an inclusive spectrum management technology that can facilitate efficient spectrum sharing. We introduce our innovative solutions that enable spectrum sharing in two ways. Firstly, our cutting-edge NextG AI-driven spectrum database creates a new spectrum awareness service that ensures effective management of the spectrum. Secondly, our spectrum exploitation techniques leverage satellite artifacts that embed unique attributes in the RF signal transmitted from each satellite, enabling coexistence with other networks. Our innovations have been tested and evaluated in a real-world satellite network, providing compelling evidence of their efficacy. With these groundbreaking solutions, we are confident that we can overcome the challenges of managing the radio spectrum and drive forward a new era of progress and innovation in both terrestrial and space networks.

Related vertical(s): IoT | Space connectivity

The post 6G | Space: New spectrum and sharing appeared first on Microsoft Research.

Related projects

Smart Surface

We explore the connections between reflective / metamaterial surfaces and next-generation wireless networks. 6G wireless network promises much faster and better wireless connectivity to cover residential, commercial, and industrial environments, as it uses larger bandwidth and higher wireless frequencies, e.g., mmWave, cmWave, and terahertz. However, the propagation of these high frequency wireless signals is heavily subject to the environment. The distribution of wireless signal strength is random and uneven across the covered area due to the ambient reflectors, blockage, and moving objects like human body. Thus, maintaining a consistent high throughput broadband wireless channel between the user and the access point is challenging. We ask – “Can we establish consistent high-throughput connections for terahertz and cmWave communication in a low-cost and scalable way?” Stay tuned.

Related vertical(s): New spectrum and sharing

The post 6G | Space: Smart surfaces appeared first on Microsoft Research.

Related projects

Artificial intelligence training in space

Large-scale deployments of low Earth orbit satellites collect massive amount of Earth imageries and sensor data, but it is increasingly infeasible to download all the high-resolution images and train the corresponding AI models on the ground. In this project, we focus on novel distributed and federated learning frameworks (opens in new tab) that enables ground stations and satellites collaboratively train AI models without downloading all the data to the ground.

Related vertical(s): Edge computing

Cloudification of network stack for IoT in space

The “new space” revolution is bringing about a new era of innovation and possibility in the industry as private companies are pushing the boundaries of what is possible by launching thousands of Low Earth Orbit (LEO) satellites. One of the most exciting developments is the use of small IoT picosatellites (picosats) that envisions offering a cost-effective way to connect millions of IoT devices around the world that may not have access to terrestrial networks. The small size and low-complexity hardware of these satellites make them easy to build and launch into orbit, resulting in rapid scaling of IoT picosat networks. As picosat constellations scale, their traditional networking stack becomes the bottleneck because it does not incorporate constraints specific to picosat constellations. In this project, we innovate a new end-to-end networking stack for IoT in space by introducing cloudification of the network stack.

Related vertical(s): IoT

Context-aware compression of satellite imagery in space

Transmitting raw space imagery data to the ground for processing presents difficulties due to limited network bandwidth, resulting in data being captured in restricted modes and taking hours to days to downlink. To address this, compression right in space is a more promising approach to reduce the amount of data transmitted. However, current compression techniques treat all pixels as having equal weight, despite not all parts of an image being equally important. Our proposed solution, Earth+, is a smart filtering and compression method that is implemented directly on the satellite. Earth+ leverages the rich historical dataset on earth to intelligently select a reference image that best represents the near future and uploads it to the satellite. Utilizing lightweight context-aware cloud detection and diff-based comparison, Earth+ identifies only the changed areas and transmits them back to earth, thereby significantly reducing data transmission volume.

Related vertical(s): Edge computing

FoodVibes: Wireless sensing and communication for food supply chain traceability

At Microsoft Research, we are working towards a fully digitized and connected supply chain for agriculture and food. With the growing human population, there is a need to responsibly and sustainably meet the global food demands. Towards this goal, FoodVibes identifies critical traceability points in the global Agri Food Industry that are responsible for inefficiency and applies technological innovation to address key challenges faced by the industry. By leveraging our research in wireless communication, battery-free and IoT sensing, we are establishing traceability for key metrics related to nutrition, sustainability, and quality of the food that nourishes the global population. Some of these key challenges being addressed include creating traceability from farm to fork, especially for bulk commodities like grain, tracking the produce environment during transport and storage with novel sensing infrastructure and a communication scheme to ensure global connectivity to support this supply chain.

Related vertical(s): IoT | Ultra-low-power connectivity

Kodan: Edgifying satellite applications for on-board computation in space

The decreasing costs of deploying space vehicles to low-Earth orbit have led to the emergence of large constellations of satellites. However, the high speeds of the satellites, the large sizes of image data, and the short ground station contacts have created a challenge for data downlink. Orbital edge computing (OEC) can filter data at the space edge and address the downlink bottleneck, but it shifts the challenge to the limited computation capacity onboard satellites. We present Kodan, an OEC system designed to maximize the utility of saturated satellite downlinks while mitigating the constraints of the computational bottleneck. Kodan has two phases: a one-time transformation step that uses a reference implementation of a satellite data analysis app, along with a representative dataset, to produce a set of specialized ML models targeted for deployment to the space edge. After deployment to a target satellite, a runtime system dynamically selects the best specialized model for each data sample to maximize valuable data downlinked within the constraints of the computational bottleneck.

Related vertical(s): Edge computing

Low latency distributed downlink for low Earth orbit satellites

Low Earth orbit (LEO) satellites for Earth observation and IoT have become very popular in recent years. The earth observation satellites collect hundreds of Gigabytes of imagery during their orbit. This data needs to be downloaded using ground stations on Earth. However, due to the low altitudes, the satellites move fast with respect to a ground station on Earth, and consequently, have a few minutes time window to download the data to a single station. Although an LEO IoT satellite aggregates comparatively much lower amount of data, it uses very low data rate link to download the data. It, in turn, has a very negative impact on the freshness of data and overall throughput of the satellite networks. We propose a geographically distributed ground station design, DGS that improves robustness and reduces downlink latency. DGS is the first system to use a hybrid ground station model, where only a subset of ground stations are uplink-capable.

Related vertical(s): IoT

Spectrum sharing between satellite and terrestrial networks

In a world where space and terrestrial networks are expanding at an unprecedented pace, it is critical to ensure that the radio spectrum, a finite resource, is utilized to benefit both types of networks. To achieve this, it is essential to have an inclusive spectrum management technology that can facilitate efficient spectrum sharing. We introduce our innovative solutions that enable spectrum sharing in two ways. Firstly, our cutting-edge NextG AI-driven spectrum database creates a new spectrum awareness service that ensures effective management of the spectrum. Secondly, our spectrum exploitation techniques leverage satellite artifacts that embed unique attributes in the RF signal transmitted from each satellite, enabling coexistence with other networks. Our innovations have been tested and evaluated in a real-world satellite network, providing compelling evidence of their efficacy. With these groundbreaking solutions, we are confident that we can overcome the challenges of managing the radio spectrum and drive forward a new era of progress and innovation in both terrestrial and space networks.

Related vertical(s): IoT | New spectrum and sharing

The post 6G | Space: Space connectivity appeared first on Microsoft Research.

Related projects

Echo: Ultra low-power satellite communication

Project Echo is focused on developing ultra-low-power satellite communication to reliably connect devices in resource constrained environments. We believe that these new wireless communication techniques will lead to the next generation of IoT devices for applications ranging from smart agriculture to communication in space.

Related vertical(s): IoT

FoodVibes: Wireless sensing and communication for food supply chain traceability

At Microsoft Research, we are working towards a fully digitized and connected supply chain for agriculture and food. With the growing human population, there is a need to responsibly and sustainably meet the global food demands. Towards this goal, FoodVibes identifies critical traceability points in the global Agri Food Industry that are responsible for inefficiency and applies technological innovation to address key challenges faced by the industry. By leveraging our research in wireless communication, battery-free and IoT sensing, we are establishing traceability for key metrics related to nutrition, sustainability, and quality of the food that nourishes the global population. Some of these key challenges being addressed include creating traceability from farm to fork, especially for bulk commodities like grain, tracking the produce environment during transport and storage with novel sensing infrastructure and a communication scheme to ensure global connectivity to support this supply chain.

Related vertical(s): IoT | Space connectivity

SatSense: Sensing the Environment using Satellites

Project SatSense is focused on using satellite telemetry to develop new techniques for environmental monitoring. We believe this will lead to gaining accurate insights about today’s ecosystem at large-scale including forestry, agriculture, oil & gas, among others.

Related vertical(s): IoT

The post 6G | Space: Ultra low-power connectivity appeared first on Microsoft Research.

(opens in new tab)

Research for Industry at Microsoft Research Summit

For 30 years, our research community at Microsoft has worked across disciplines, institutions, and geographies to envision and realize the promise of new technologies for Microsoft and for society. Today, we’re inviting the global science and technology community to continue this exploration—because ensuring that future advancements benefit everyone is up to all of us.

The Research for Industry track, scheduled on Day 2 – October 20, will discuss the data-driven future of industry, and the interdisciplinary research opportunities in various industries, such as space, Telco’s, energy, supply chain, agriculture, food, financial services and entertainment. Hear about our innovations, and thoughts from industry leaders from academia, government agencies, and global industry-leading companies, including:

On October 20, this track will take place in three broadcast regions:

• 11:00 AM–4:30 PM China Standard Time (UTC+8),
• 10:00 AM–3:30 PM British Summer Time (UTC+1), and
• 9:00 AM–2:30 PM Pacific Time (UTC-7)

Once registered, you can view the session scheduler, select the broadcast region nearest you, and add the Research for Industry track to your event schedule. Learn more about Microsoft Research Summit (opens in new tab).

Opens in a new tab

The post Research for Industry at Research Summit appeared first on Microsoft Research.

Global food production needs to increase by 50% by 2050 compared to today’s levels to feed the growing population of the world. And, we need to meet this demand despite the limited amount of arable land and receding water levels, and while reducing the impact to the environment. This problem is even more severe if we consider the challenge of nourishing the world, instead of just feeding the world.

Farming worldwide, including in the developed world, relies heavily on the instinct and guesswork of farmers, instead of the ground truth and farm data. For example, the amount of fertilizer applied in the farm is often based on previous year’s yield instead of the nutrient requirements of the soil. Farmers typically spray water and pesticide uniformly throughout the farm, instead of where they are needed.

One of the most promising approaches to address this challenge is data-driven agriculture. Using the latest advances in AI and cloud computing a farmer can learn about when to sow the seed, what pests are likely to occur in their fields, and use precision agriculture techniques to apply farm inputs such as water, nutrients, and pesticides. These advances will help the farmer increase yields, reduce costs, grow revenue, and employ sustainable agriculture practices. This will also drive the employment of people managing the farm network, and digital advisory services.

Additionally, the world also has a nutrition problem. Per the Global Nutrition Report, more than a third of reproductive age women are anemic, and 39% adults are overweight or obese. It is estimated that malnutrition could cost society up to $3.5 trillion per year. Even in the developed world, diets high in sugary drinks, fast food, and refined grains are main contributors to heart disease, diabetes, and obesity.

However, there is no solution that fits every individual. Studies have shown that the glucose and triglyceride levels vary differently for individuals, even after eating the same meal. The current trend of Keto or celebrity diet or food pyramid only works for a fraction of the population. This variation is a result of the individual’s microbiome, and other factors.

A potential solution to this malaise is personalized nutrition. It refers to personalization of the dietary intake, typically to prevent or treat chronic diseases, based on age, race, gender, DNA, health history, and lifestyle. The best diet for one individual might be very different than the best diet for another.

We believe in a future of food in which:

• Every person in the world gets right amount of calories
• The food contains the adequate nutrients
• Consumers treat food as preventive medicine
• … all of this without compromising taste!

Opportunities from feeding to nourishing

To achieve food and nutrition security, we need to:

• Grow more food in the same amount of arable land
• Ensure food is not wasted in the supply chain
• Learn nutritional deficiencies and provide recommendations
• Ensure nutritious and personalized food is delivered to every person

One way to achieve the above is by making the food supply chain data driven. If we can capture data from every component of the food supply chain, and securely share with other parts of the supply chain, and analyze it using the latest AI algorithms, it will help drive efficiencies in each component, for example, to grow more food sustainably in the farm, enable track and trace, reduce food waste, improve productivity in food processing plants, and synthesize new food.

Azure FarmBeats (opens in new tab) allows on-farm data to be collected and analyzed using AI for digital advisories to growers. While this gives us a head start compared to competition, we need to do a lot more, as shown in figure 1, to get to the vision of personalized, healthy food production and consumption.

Driving the future of food at Microsoft

Microsoft will take a combined research + engineering approach to help this important industry meet challenges in this industry. We will build differentiated tech that can help bring data to drive efficiencies across these areas of the entire food chain.

1. Supply chain: Once a produce is harvested, we lose all information about how it was grown, e.g. when it was planted, whether it was watered, what chemicals were applied, etc. However, the nutrient content of the produce depends in large part on the way it was grown.
2. Sustainability: There is a need to make farming sustainable -70% of global water resources are needed for Agriculture, 24% of global greenhouse emission comes from Agriculture. 251T liters of water to be saved in 2030 from implementing Smart Agriculture.
3. Personalizing food for the consumer: The food needs to be personalized for nutrition and taste. Gut microbiome tests can reveal the best food for a customer, which can then be used to personalize food for the customer. Furthermore, the food needs to taste good as well.
4. Emerging markets: Faster genome sequencing and analysis, with the advent of CRISPR tech, has led to the development of new seeds and soil biologicals, and development of ingredients that can help fix the flavor, fragrance, or sweetness. This process involving computational chemistry and molecular discovery is very time consuming. Food companies spend billions of dollars in R&D for the development of new ingredients.

Opens in a new tab

The post Agriculture and food appeared first on Microsoft Research.

Gaming technologies have a deep intersection with AI and simulations are a powerful and cost-effective approach to generate data to train and test AI techniques and models. We focus on research in this space because we recognize that these technologies are broadly relevant and applicable to empowering competitive innovation for our customers and partners in many industries.

A particularly intriguing opportunity lies in techniques that use physics simulation and AI as complementary capabilities. Our researchers working on Project Paidia are using reinforcement learning to train AI agents faster-than-real-time within physically simulated game worlds. In another effort, Project Triton seeks to enable detailed and automated immersive audio using specialized wave physics algorithms running in the cloud, with ongoing research on neural net acceleration.

The escalating expectations of viewers, users, and players for immersive and realistic experiences is driving massive increases in the complexity and costs in content creation. Character animation, voice-over, prop placement, world building, audio effects, AI navigation setup are all examples of interdependent, iterative production processes that are growing more rapidly than human-driven production teams can scale. Our researchers and engineers see an opportunity for scalable immersive content production to empower creators across games, film, and TV with powerful virtual content generation and rendering tools. These tools will leverage research into new physics+AI techniques designed for the cloud, yielding instant WYSIWYG feedback and differentiated immersive experiences.

We have a range of research efforts to pursue this vision:

AI for game testing aims to use AI agents to test out game environments extensively via parallel cloud compute, with potential to drastically reducing game testing (QA) times and time-to-finding bugs, which form a significant portion of a typical game’s development cost today.

Project Mishtu unlocks last-mile media content delivery for low-connectivity regions in emerging markets. In a recent successful pilot, a major media platform in India uploaded its content library to Azure, which was processed and downloaded to secure hubs that can provide content through local retailers to consumers lacking sufficient internet connectivity.

Project Paidia: reinforcement learning for game AI involves a collaboration with multiple Xbox game studios to examine modern reinforcement learning methods to build AI agents that can compete and collaborate intuitively with humans, potentially providing a major leap in the realism of game experiences. This would be a notable advance over most non-playing game characters today that use rudimentary AI systems based on hand-coded state machines.

Project Triton: immersive sound propagation simulates audio propagation in virtual environments, simultaneously reducing production costs away from manual markup, while boosting audio detail for gamers with immersive audio cues. It has shipped in multiple flagship games (Gears of War, Sea of Thieves, Call of Duty) and in active use within the HoloLens team. The tech is evolving towards scaling to massive and dynamic worlds.

Synthetic data generation for training speech AI explores synthetics for acoustics. Cloud wave simulation was used to generate numerous responses in synthetic conference rooms, something that is very expensive to do in the real world. The responses were used to augment the training dataset for Microsoft Teams’ recently shipped background noise suppression feature.

Watch For: live video analytics is a scalable media analysis platform built on Azure, operating production services for Bing, MSN, Mixer, and Xbox, analyzing large volumes of images, videos, and livestreams reaching tens of millions of users (for example: Mixer HypeZones, Bing’s Live Stream Search, MSN Esports Hub).

Read more in the Research Collection – Shall we play a game?Opens in a new tab

The post Media and entertainment appeared first on Microsoft Research.