• I currently work as a Software Engineer / Researcher at Google.


    I obtained my PhD in Electrical and Computer Engineering at Carnegie Mellon University advised by Professor Pei Zhang and Professor Raj Rajkumar.


    My research focuses on networked embedded systems - occasionally flying ones; bringing together a broad set of interests that include sensors, distributed systems, wireless communications, indoor localization and robotics.

    Aveek Purohit


  • Publications

    Peer-reviewed Conferences and Workshops

    1. [Sensys] Xinlei Chen, Aveek Purohit, Carlos Ruiz Dominguez, Stefano Carpin, Pei Zhang. “DrunkWalk: Collaborative and Adaptive Planning for Navigation of Micro-Aerial Sensor Swarm.” In the 13th ACM Conference on Embedded Networked Sensor Systems (SenSys), Seoul, South Korea, November 2015.
    2. [RSN] Aveek Purohit., Stefano Carpin and Pei Zhang. Adaptive Planning for Deployment of Micro-Aerial Sensor Swarms. International Workshop on Robotic Sensor Networks, part of Cyber-Physical Systems Week, 2014. [pdf]

    3. [ICRA] Aveek Purohit, Pei Zhang, Brian M. Sadler, Stefano Carpin, “Deployment of Swarms of Micro-Aerial Vehicles: from Theory to Practice”, 2014 IEEE International Conference on Robotics and Automation (ICRA), 2014. [pdf]

    4. [MobiSys] Zheng Sun, Aveek Purohit, Raja Bose, and Pei Zhang. “Spatial-Aware Interaction for Mobile Devices Through Energy-Efficient Audio Sensing.” In the 11th Annual International Conference on Mobile Systems, Applications and Services. ACM MobiSys, Taipei, Taiwan, June, 2013. [pdf]

    5. [SECON] Aveek Purohit, Zheng Sun, Shijia Pan and Pei Zhang. SugarTrail : Indoor Navigation in Retail Environments without Surveys and Maps. To appear in the Tenth IEEE Conference on Sensing, Communication, and Networking (SECON 2013), New Orleans, USA, June 2013. [pdf]
    6. [IPSN] Aveek Purohit, Zheng Sun, and Pei Zhang. “SugarMap: Location-less Coverage for Micro-Aerial Sensing Swarms.” In the 12th International Conference on Information Processing in Sensor Networks. ACM/IEEE IPSN, Philadelphia, PA, April 2013. [pdf]
    7. [HotMobile] Zheng Sun, Aveek Purohit, Shijia Pan, Frank Mokaya, Raja Bose, and Pei Zhang. “Polaris: Getting Accurate Indoor Orientations for Mobile Devices Using Ubiquitous Visual Patterns on Ceilings.” In The Thirteenth Workshop on Mobile Computing Systems and Applications (HotMobile 2012). [pdf]
    8. [Ubicomp Workshop] Pei Zhang and Aveek Purohit. “The Cloud Meets the Crowd: A Framework for Distributed Cloud Sensing”. In the Workshop on Mobile Sensing: Challenges, Opportunities and Future Directions, held in conjunction with the 13th ACM International Conference on Ubiquitous Computing (Ubicomp), Beijing, China, September 2011.
    9. [Ubicomp] Zheng Sun, Aveek Purohit, Kaifei Chen, Shijia Pan, Trevor Perring, and Pei Zhang. “PANDAA: Physical Arrangement Detection of Networked Devices through Ambient-Sound Awareness”. In the 13th ACM International Conference on Ubiquitous Computing (Ubicomp), Beijing, China, September 2011. (Affiliated demo received the Best Demo Award) [pdf]
    10. [IWCMC Workshop] Aveek Purohit and Pei Zhang. “Controlled-Mobile Sensing Simulator for Indoor Fire Monitoring”. In the First IEEE Workshop on Design, Modeling and Evaluation of Cyber Physical Systems (CyPhy'11), Istanbul, Turkey, July 2011. [pdf]
    11. [IPSN] Aveek Purohit, Zheng Sun, Frank Mokaya, and Pei Zhang. SensorFly: Controlled-mobile Sensing Platform for Indoor Emergency Response Applications. In the 10th International Conference on Information Processing in Sensor Networks. ACM/IEEE IPSN, Chicago, IL, April 2011. [pdf]
    12. [IPSN] Aveek Purohit, Bodhi Priyantha, and Jie Liu. WiFlock: Collaborative Group Discovery and Maintenance in Mobile Sensor Networks. In the 10th International Conference on Information Processing in Sensor Networks. ACM/IEEE IPSN, Chicago, IL, April 2011. [pdf]
    13. [Mobisense] Zheng Sun, Aveek Purohit, Kathleen Yang, Neha Pattan, Dan Siewiorek, Asim Smailagic, Ian Lane, and Pei Zhang. “CoughLoc: Location-Aware Indoor Acoustic Sensing for Non-Intrusive Cough Detection”. In the International Workshop on Emerging Mobile Sensing Technologies, Systems, and Applications. Mobisense, San Francisco, CA, June 2011. [pdf]



    1. [SIGCOMM] Zheng Sun, Aveek Purohit, Philippe De Wagter, Irina Brinster, Chorom Hamm, and Pei Zhang. “(Demo abstract) PANDAA: A Physical Arrangement Detection Technique for Networked Devices through Ambient-Sound Awareness”. In the conference of the ACM Special Interest Group on Data Communication (SIGCOMM), Toronto, ON, Canada, August 2011.
    2. [MobiSys] Zheng Sun, Aveek Purohit, KathleenYang, Neha Pattan, Dan Siewiorek, Asim Smailagic, Ian Lane, and Pei Zhang. “(Poster) VMA: Indoor Acoustic Sensing Platform for In-home Patient Monitoring”. In the 8th Annual International Conference on Mobile Systems, Applications and Services. ACM MobiSys, San Francisco, CA, June, 2010.
    3. [Sensys] Aveek Purohit and Pei Zhang. 2009. SensorFly: a controlled-mobile aerial sensor network. In Proceedings of the 7th ACM Conference on Embedded Networked Sensor Systems (Berkeley, California, November 04 - 06, 2009). SenSys '09. ACM, New York, NY, 327-328. (Best Demo Award)


    1. “Next frontier in emergency response”, NBC NEWS, Jan 2014 [Link]
    2. “Always On: Helibots to the rescue!”, CNET TV, July 2012 [Link]
    3. “Carnegie Mellon's flying robots”, CBS SMART-PLANET, May 2011[Link]
    4. Featured on Sci Fi Science, DISCOVERY SCIENCE CHANNEL, Sep 2010 [Preview]
    5. “Swarm Bots”, BBC FOCUS MAGAZINE, Mar 2010 [Link] [pdf]
    6. “Aerobot Invasion: World’s Newest & Most Spectacular Unmanned Aircraft”, POPULAR SCIENCE, Mar 2010
    7. “Networked surveillance minicopters can't be kept down”, NEW SCIENTIST, Nov 2009 [Link]
    8. “SensorFly robots hunt in packs and can take a battering”, WIRED, Nov 2009 [Link]
    9. “Self-righting autonomous swarming robots”, MAKEZINE, Nov 2009 [Link]
    10. “SensorFly survives racket beatdown”, BOT JUNKIE, Nov 2009 [Link]
    11. “SensorFly Wins Best Demo at SenSys 2009”, Carnegie Mellon CIT Feature, Nov 2009 [Link]
    12. “SensorFly for Hazardous Situations”, Carnegie Mellon Homepage Stories, Aug 2009 [Link]


    1. “SensorFly”, Talks on Computing Systems, Carnegie Mellon Silicon Valley, March 2009 [Link]
  • Research

    broken image

    Controlled-Mobile Aerial Sensor Networks

    The SensorFly is a novel low-cost controlled-mobile aerial sensor networking platform. A flock of these 29g autonomous helicopter nodes with communication, ranging and collaborative path determination capabilities, can be extremely useful in sensing survivors after disasters or adversaries in urban combat scenarios.

    The platform is under active development. We are currently designing and prototyping the 5th generation of SensorFly hardware and software. The software and hardware schematics are open source and available through our GitHub repository. Stay tuned!


    [IPSN 2011 Paper]

    broken image

    SugarMap: Location-less Coverage for Micro-aerial Sensing Swarms

    SugarMap enables resource-constrained MAV nodes to achieve efficient sensing coverage. The self-establishing system uses approximate actuation models of mobile nodes in conjunction with radio signatures from self-deployed stationary anchor nodes to create a common coverage map. Consequently, the system coordinates node movements to reduce sensing overlap and increase the speed and efficiency of coverage. The system uses particle filters to account for uncertainty in sensors and actuation of MAV nodes, and incorporates redundancy to guarantee coverage.


    [IPSN 2013 Paper]

    broken image

    WiFlock: Collaborative Group Discovery and Maintenance

    Low energy neighbor discovery, group formation, and group maintenance is a fundamental service in mobile sensor networks. Traditional solutions consider these protocols separately. WiFlock is an energy-efficient protocol that combines discovery and maintenance using a collaborative beaconing mechanism. WiFlock combines a coordinated synchronized listening and evenly-spaced transmission (SLEST) schedule effectively with one-way discovery beacons to fulfill both purposes. We show that shorter listening duration implies smaller discovery latency and faster group information propagation. We evaluate WiFlock on a 50-node test bed with nodes running at 0.2% duty cycles. We show that WiFlock has shorter discovery latency and better scalability than previous approaches.


    [IPSN 2011 Paper]

    broken image

    SugarTrail: Survey-free Indoor Navigation in Retail Environments

    SugarTrail is a system for indoor navigation assistance in retail environments that minimizes the need for active tagging and does not require existing maps. By leveraging the structured movement patterns of shoppers in retail store environments, the system provides higher accuracy than existing radio finger-printing approaches. With minimal setup and no active user participation, the system automatically learns user movement pathways in indoor environments from radio-frequency and magnetic signatures. These pathways are clustered and used to automatically build a navigable virtual roadmap of the environment.


    [SECON 2013 Paper]

    broken image

    PANDAA: Zero-Config Device Arrangement-Detection

    PANDAA is a zero-configuration spatial localization system for networked devices based on ambient sound sensing. After initial placement of the devices, ambient sounds, such as human speech, music, footsteps, finger snaps, hand claps, or coughs and sneezes, are used to autonomously resolve the spatial relative arrangement of devices using trigonometric bounds and successive approximation. Using only time difference of arrival measurements as a bound for successive estimations, PANDAA is able to achieve an average of 0.17 meter accuracy for device location in the meeting room deployment.


    [UbiComp 2011 Paper]

    broken image

    Point: Spatially-Aware Interaction for Mobile Devices

    Using built-in microphones and speakers on commodity mobile devices, Spartacus uses a novel acoustic Doppler-effect based technique to enable users to accurately initiate an interaction with a neighboring device through a pointing gesture. Experimental results show that Spartacus achieves an average 90% device selection accuracy within 3m for most interaction scenarios.


    [Mobisys 2013 Paper]

    broken image

    Polaris: Accurate Indoor Orientations using Ceiling Patterns

    Polaris is a system for providing accurate orientations for mobile phones in indoor environments using ubiquitous ceiling patterns in a building as orientation references. Though digital compasses are commonly used in mobile phones to determine device orientations, they are vulnerable to indoor magnetic interference. Since ceiling patterns are universal and unrelated to magnetic fields, Polaris can provide accurate orientations for mobile devices even under severe magnetic interferences. The achieved accuracy is over 4.5 degree, 3.5X better than raw compass readings.


    [HotMobile 2012 Paper]

    broken image

    Over-the-air Incremental Sensor Network Reprogramming

    An over-the-air sensor network reprogramming system for Sensor Andrew, Carnegie Mellon’s campus-wide wireless sensor network. The system’s incremental binary patch update capability reduces communication and hence energy on average by 70%, for reprogramming resource constrained sensor nodes. Available as part of the Nano-RK real-time WSN operating system source code.