Affordable and Capable Search and Rescue Robots

$3,040
Raised
51%
Ended on 4/02/17
Campaign Ended
  • $3,040
    pledged
  • 51%
    funded
  • Finished
    on 4/02/17

About This Project

Our goal is to build affordable teams of robots for disaster relief. We believe that the computing and sensing capabilities of Android smartphones make an inexpensive, yet highly capable robotic platform. The idea is to combine the wide range of commercially available platforms with the power of an Android phone. With these robots, we plan to test neurobiologically inspired algorithms for planning and object identification, which are useful for search and rescue missions.

Ask the Scientists

Join The Discussion

What is the context of this research?

Earthquakes, chemical leaks, the tsunami that led to the Fukushima nuclear radiation leak, are examples of disasters that take a huge toll on people and the economy. Disaster relief is highly risky and costly for human first responders. As an alternative, robots could aid the search and rescue process. However, current robot solutions are very expensive to deploy and out of reach for many communities. Furthermore, current algorithms for robot control are not yet able to handle the complex demands of a disaster area. Our work on developing smart, affordable robots may allow more communities to purchase and deploy teams of robots to safely assess damage and find survivors.

What is the significance of this project?

Most robot solutions are brittle and need human intervention, which is not possible in many disaster zones. This is a stark contrast to how animals approach problems. Animals can learn from experience, they are flexible and adaptable, and they work well in teams. These qualities could be very useful for providing disaster relief and carrying out search and rescue missions. We take inspiration from these animal models, and create neurobiologically inspired algorithms that demonstrate many of these attributes.

What are the goals of the project?

We have designed many of the algorithms necessary and tested them on single robots. These algorithms are related to how animals plan, tradeoff between risky and conservative behavior, and identify and respond to novel objects or events. One goal is to tailor these algorithms to disaster relief and deploy them on robot teams. To date, we have built 3 robots for this purpose, but this is not enough to cover a large space. A second goal is to construct 5 more robots to create a team of 8. Communication lines are often down or impaired in a disaster. Smartphones have the capability to communicate locally. The third goal is to use the phone's communication capabilities to create a network "on the fly". This network can be monitored by disaster relief workers.

Budget

Please wait...

Our budget will help us create the robot team. We currently have 3 search and rescue robots. But, we would like that number to be closer to 10 robots. Each robot costs $900 in parts and needs an Android smartphone, which can bought for roughly $300. The instructions and parts list can be found at: http://www.socsci.uci.edu/~jkrichma/ABR/

Endorsed by

Robots have already been deployed to help in disasters like the 2001 collapse of the World Trade Center, Hurricane Katrina, the Deepwater Horizon oil spill, and the 2011 Japanese earthquake and tsunami. But usually there are only a few of them, and it takes days or weeks to get them there. What if the robots were cheap and small and every response agency had hundreds sitting around in different regions, waiting to be deployed at a moments notice? Imagine the good that could come of that, and then support this project.
I love that this project combines the elements of (1) robots in the real world, (2) a realistic and valuable application, (3) a neuro-biologically inspired approach, and (4) students who can take the ideas out of the university and into the real world.
This is an important project. It will develop useful technology relieving first responders from highly risky environments and activities following disasters, yet still assess damage and find survivors. The research team is eminently qualified to do this work, and students will be engaged in research integrating cognitive science, computer science, and engineering.
This is an extremely useful project that will find applications far beyond first responders, though giving such robotic tools to first responders is probably the best initial application.

Meet the Team

Jeff Krichmar
Jeff Krichmar
Professor

Affiliates

Department of Cognitive Sciences, Department of Computer Science, University of California, Irvine
View Profile
Xinyun Zou
Xinyun Zou
1st-year PhD Student

Affiliates

Department of Computer Science, University of California, Irvine
View Profile
Nick Pereira
Nick Pereira
4th-year B.S. Mechanical Engineering

Affiliates

University of California, Irvine
View Profile
Tiffany Hwu
Tiffany Hwu
3rd Year PhD Student

Affiliates

Department of Cognitive Sciences University of California, Irvine
View Profile
Alex Wang
Alex Wang
Guy Nimrodi
Guy Nimrodi
4th year undergraduate student

Affiliates

UC Irvine
View Profile

Jeff Krichmar

I am a professor in the Department of Cognitive Sciences and the Department of Computer Science at the University of California, Irvine. I have spent nearly 20 years trying to understand how the brain works and to use this knowledge to create intelligent systems. My research interests include brain-based robots or neurorobots, and mathematical models of brain function. I have a passion for getting students excited at an early age in Science, Technology, Engineering, and Math (STEM).

To help with STEM education, my group has developed inexpensive, yet highly capable robots built around Android Smartphones. Building instructions, software examples, and other information can be found at:

http://www.socsci.uci.edu/~jkrichma/ABR/

To pursue the goal of better understanding the brain through mathematical, my group has created and supports a simulation environment for developing large-scale brain models, which is available at:

http://www.socsci.uci.edu/~jkrichma/CARLsim/.


Xinyun Zou

I received a B.S.E. in Electrical & Computer Engineering and Biomedical Engineering and a minor in Economics from Duke University in 2016. I spent the last two years at Duke working on an independent research project on biologically-plausible Hodgkin-Huxley multi-compartment neuron modeling with external stimuli, as well as collaborating with a PhD student on SNN-controlled locomotion of a virtual hexapod. I currently am a first-year PhD student in the Department of Computer Science at the University of California, Irvine. My research interests include neurorobotics, applications of biologically plausible models on embedded devices, emotional processing of robotics, and human-robot interaction.

Nick Pereira

I am a senior level undergrad student working towards a B.S. in Mechanical Engineering at the University of California, Irvine. I interned in a Quality Engineering department for Satellite applications in 2015 and assisted my dad in starting a handyman business in the summer of 2016. In addition to my full time student status, I continue to develop my automotive and robotics hobbies. I am working with Professor Krichmar, Tiffany, Xinyun, Guy and Alex on the Android Based Rescue Robotics program for my senior design project.

Tiffany Hwu

I am a 3rd Year PhD Student in Cognitive Sciences at the University of California, Irvine. I received a B.A. in Computer Science and Cognitive Science at the University of California, Berkeley, where I worked on a Bayesian music recommender system based on a psychological model of similarity judgment. I continue to research cognitive science applications to real world problems, such as search and rescue missions and self-driving cars. My current research interests include biologically inspired spatial navigation, transfer learning, neurorobotics, and decision making.

Guy Nimrodi

I am a senior Mechanical Engineering undergraduate student at the University of California, Irvine. I have nearly 2 years of experience interning in industry leading Medical Device companies. During the summer of 2015, I worked at a Robots and BioMedical MicroSystems laboratory at the University of Tel Aviv, Israel. I am currently a development engineering intern at NuVasive in San Diego and a member of the Rescue Robotics Ground team at UCI.

Lab Notes

Nothing posted yet.

Additional Information

We thank you for your support. As an added bonus, anyone who contributes over $500 will receive a fully assembled Android Based Robot (phone not included) built with a Rover 5 robot base.

Some relevant references:


  1. N. Adde. "Dialed In: UC Irvine Robots Leverage Smartphone Technology for Cheap, Simple Control." Unmanned Systems. 30-33, 2015.

  2. N. Oros and J. L. Krichmar, "Smartphone Based Robotics: Powerful, Flexible and Inexpensive Robots for Hobbyists, Educators, Students and Researchers," CECS Technical Report, 13-16, pp. 1-11, 2013.

  3. J. L. Krichmar, "Path Planning using a Spiking Neuron Algorithm with Axonal Delays.," in IEEE Congress on Evolutionary Computation, Vancouver, pp. 1219-1226, 2016.

  4. T. Hwu, A. Y. Wang, N. Oros, and J. L. Krichmar, "Adaptive Robot Path Planning Using a Spiking Neuron Algorithm with Axonal Delays," IEEE Transactions on Cognitive and Developmental Systems., Submitted.

  5. M. C. Avery, D. A. Nitz, A. A. Chiba, and J. L. Krichmar, "Simulation of Cholinergic and Noradrenergic Modulation of Behavior in Uncertain Environments," Frontiers in Computational Neuroscience, vol. 6, 2012.

  6. J. L. Krichmar, "The Neuromodulatory System - A Framework for Survival and Adaptive Behavior in a Challenging World.," Adaptive Behavior, vol. 16, pp. 385-399, 2008.

  7. J. L. Krichmar, "A neurorobotic platform to test the influence of neuromodulatory signaling on anxious and curious behavior," Front Neurorobot, vol. 7, pp. 1-17, 2013.

  8. M. Beyeler, N. Oros, N. Dutt, and J. L. Krichmar, "A GPU-accelerated cortical neural network model for visually guided robot navigation," Neural Netw, vol. 72, pp. 75-87, 2015.


Project Backers

  • 26Backers
  • 51%Funded
  • $3,040Total Donations
  • $116.92Average Donation
Please wait...