Lead

RFID-based enterprise intelligence

SixthSense is a platform for RFID-based enterprise intelligence that combines RFID events with information from other enterprise systems and sensors to automatically make inferences about people, objects, workspaces, and their interactions, writes Nivedan Prakash

We all are aware of the benefits that can be leveraged out of Radio Frequency Identification (RFID) technology. RFID is basically an electronic tagging technology that allows the detection and tracking of tags and consequently the objects that they are affixed to. This ability to do remote detection and tracking coupled with the low cost of passive tags has led to the widespread adoption of RFID in supply chains worldwide.

Microsoft Research India has come up with a technology called SixthSense, which is a platform for RFID-based enterprise intelligence systems. The vision behind this is the workplace or home of the future where computing is extended to encompass non-computing entities such as people, objects, and spaces to enable rich user experiences.

The technology comprises inexpensive tags that are attached to objects and readers that are able to read these tags from some distance. In SixthSense, the researchers have extended the domain of RFID to settings, such as the workplace, where there is rich interaction amongst people and between people and objects.

SixthSense has been designed and developed by Venkat Padmanabhan, Principal Researcher - Mobility, Networks and Systems Group, Microsoft Research India and Lenin Ravindranath, formerly an Assistant Researcher in the same group.

Padmanabhan said, “The idea of SixthSense is to use RFID technology in conjunction with a bunch of other enterprise systems such as the calendar system or online presence that can track user activity. Here, we consider an enterprise setting of the future where people (or rather their employee badges) and their personal objects such as books, laptops, and mobile phones are tagged with cheap, passive RFID tags, and there is good coverage of RFID readers in the workplace.”

The rationale behind coming up with this kind of technology is the underlying fact that RFID is widely used to track the movement of goods through a supply chain—whether it be pallets shipped between warehouses, cases delivered to stores, or items placed on the store shelves, thereby optimizing inventory management and yielding significant cost savings.

“If you look at the technology trends, RFID has really taken off in a big way in the world of warehouses and retail stores amongst others wherein you can tag items and then track their movement through the supply chain. Although it’s expensive, it is becoming cheaper. In the supply chain setting, there is typically a linear flow of objects. The question we asked was whether RFID technology could be used in an interesting way in a different environment like an office building or an enterprise. That’s how we started off and we basically realized that rather than working with RFID technology in isolation, it would make sense to use it in conjunction with other enterprise systems that already existed. This led to the SixthSense system,” added Padmanabhan.

Understanding the system

The key components of the SixthSense system, including the databases, inference engine, and applications, are run centrally by the enterprise. This provides the (trusted) inference engine access to the complete set of sensed data across all users, objects, and zones, allowing it to make effective inferences. Likewise, the (trusted) application is allowed the flexibility of working with a complete set of inferences (i.e., inferences pertaining to all users and their objects), yet control what processed information is presented to the users to ensure privacy.

In contrast, if the inference engine or the application were run by individual users on their own desktop machines, privacy consideration would restrict the set of information made available to these, and hence limit their functionality.

The main components of SixthSense are—the RFID monitor and other enterprise monitors like the calendar monitor, presence monitor, login monitor, and cameras; the raw database wherein the RFID monitor and the other enterprise monitors push data into the raw database; an inference engine that operates on the raw database to draw inferences about people, objects, and workspaces; the processed database which is populated by the inference engine with its inferences, making these available to applications built on top of the SixthSense platform; and lastly a set of APIs for applications to look up the inferences stored in the processed database or to receive callbacks when new inferences are made.

Workings of SixthSense

SixthSense focuses on applying RFID to an enterprise setting, such as a corporate office or university department. Unlike in a supply chain, an enterprise setting involves rich interaction amongst people, between people and objects, and between people and workspaces. For instance, people own objects such as books, cell phones, and laptops, which they often carry around and sometimes misplace.

Here, SixthSense provides a platform for tracking and inferring such interactions, and then exposing these to the higher layers via APIs that enable useful applications and services to be built. In this manner, it raises the level of abstraction for applications in this domain beyond tag-level events, akin to how RFID stacks such as Microsoft’s BizTalk do so in the supply chain context. In short, SixthSense represents a form of mobile computing applied to non-computing entities. It assumes a setting where most people (or rather their employee badges) and objects contain passive RFID tags, and that the coverage of RFID readers spans much of the workspace.

Padmanabhan said, “However, we do not assume that this tagging is always cataloged systematically. Indeed, many objects present in a workplace may not even belong to the enterprise (e.g., a user’s personal mobile phone). Even if all objects and people were cataloged, this would be a manual process, prone to errors, and furthermore would require updating each time a new object is added or an object needs to be retagged because of the deterioration of its old tag. Therefore, a key goal of SixthSense is to make all inferences automatically, without requiring any human input. Even in settings where human input is available, the inference algorithms in SixthSense can help catch errors such as the wrong ownership information for an object being recorded in a catalog.”

SixthSense incorporates algorithms that start with a mass of undifferentiated tags and automatically infer a range of information based on an accumulation of observations. The technology is able to automatically differentiate between people tags and object tags, learn the identities of people, infer the ownership of objects by people, learn the nature of different zones in a workspace (e.g., private office versus conference room), and perform other such inferences.

Mobility of people and objects is a key to the inference performed by SixthSense. For example, tags attached to people are more likely to move, with less dependence on other tags, than tags attached to objects. Likewise, the owner of an object is likely to be the person who carries it around the most.

By combining information from these diverse sources, SixthSense records all tag-level events in a raw database. The inference algorithms consume these raw events to infer events at the level of people, objects, and workspace zones, which are then recorded in a separate processed database. Applications can either poll these databases by running SQL queries or set up triggers to be notified of specific events of interest.

Some noteworthy points

SixthSense infers when a user has interacted with an object, for example, when you pick up your mobile phone. It is a platform in that its programming model makes the inferences made automatically available to applications via a rich set of APIs. To demonstrate the capabilities of the platform, the researchers have prototyped a few applications using these APIs, including a misplaced object alert service, an enhanced calendar service, and rich annotation of video with physical events.

For future work, the goal is to deploy SixthSense on a more extensive RFID setup that also covers shared spaces such as conference rooms and hallways. They are also planning to refine their programming model, as they gain experience with more applications.

nivedan.prakash@expressindia.com