Post-Doctoral Research

1) Team MIT: DARPA Robotics Challenge Trials (Finished 4th)

• M. Fallon, S. Kuindersma, S. Karumanchi, M. Antone, T. Schneider, H. Dai, C. Perez-D’Arpino, R. Deits, M. DiCicco, D. Fourie, T. Koolen, P. Marion, M. Posa, A. Valenzuela, P. Kuan-Ting Yu, J. A. Shah, K. Iagnemma, R. Tedrake, S. Teller, "An Architecture for Online Affordance-based Perception and Whole-body Planning", Journal of Field Robotics (JFR) (Special Issue on DARPA Robotics Challenge Trials), 2014.

2) Team MIT: DARPA Virtual Robotics Challenge (Finished 3rd)

• R. Tedrake, M. Fallon, S. Karumanchi, S. Kuindersma, M. Antone, T. Schneider, T. Howard, M. Walter, H. Dai, R. Deits, M. Fleder, D. Fourie, R. Hammoud, S. Hemachandra, P. Ilardi, C. Perez-D’Arpino, S. Pillai, A. Valenzuela, C. Cantu, C. Dolan, I. Evans, S. Jorgensen, J. Kristeller, J. A. Shah, K. Iagnemma, S. Teller, “A Summary of Team MIT’s Approach to the Virtual Robotics Challenge”, IEEE International Conference on Robotics and Automation, 2014. [pdf][watch on youtube]

3) Mobility Erosion : Guaranteed Motion Safety in environments with hard and soft hazards.

I have been developed a min-max morphological operation that generalizes obstacle growing used in motion planning to soft spaces (space of speed limits). This is termed as Mobility Erosion.

1. Starts with an initial mobility map

2. Erodes away excess mobility based on estimates of worst case stopping distance.

3. Eroded mobility map provides speed limits as a function of position and heading. When adhered to, safety is guaranteed.

At high speeds need to take into account the following (in addition to vehicle size and shape):

• stopping distance

• latency (actuators and comms)

• position uncertainty

• S. Karumanchi, K. Iagnemma, and S. Scheding, “Mobility Erosion: High Speed Motion Safety for Mobile Robots Operating in Off-Road Terrain”, IEEE International Conference on Robotics and Automation, 2013. [pdf]

4) Solving a boundary value problem using a reactive controller.

Mobility Erosion can also be used to create reactive controllers that can generate sub-optimal trajectories to a goal. The controller generalizes to soft hazards and the tuning parameters are environment invariant.

• S. Karumanchi and K. Iagnemma , "Reactive control in environments with hard and soft hazards", IEEE Intelligent Robots and Systems, 2012 [pdf].

5) Operator assist algorithms for tele-operation

[More details in: MIT news]

• S.J. Anderson, S. Karumanchi , K. Iagnemma, “Constraint-Based Planning and Control for Safe, Semi-Autonomous Control of Vehicles”, Proceedings of 2012 IEEE Intelligent Vehicles Symposium, June 2012, Alcalá de Henares, Spain. [pdf]