Congratulations to lab member Karthikeya Parunandi on successfully defending his master’s thesis. Karthikeya’s thesis was on ‘Perturbation Feedback Approaches in Stochastic Optimal Control: Applications to Model-based and Model-free Problems in Robotics’.
Our paper “T-PFC: A Trajectory-Optimized Perturbation Feedback Control Approach” has been accepted for publication in Robotics and Automation Letters (RA-L) and also for presentation at IROS-2019, which will be held at Macau, China.
Lab member Karthikeya presents work on “Robust Pose-Graph SLAM Using Absolute Orientation Sensing” (published in IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 981-988) at ICRA 2019 held at Montreal, Canada. Link to the poster: link
Congratulations to EDP lab member Dilshad Raihan on successfully defending his Ph.D. Dilshad’s thesis was on ‘Particle Gaussian mixture filters for general nonlinear non-Gaussian Bayesian estimation’. He will be employed as a Data scientist at Anadarko Petroleum Corporation.
Our heartiest congratulations to EDP Lab member Saurav Agarwal who successfully defended his Ph.D. on Dec 6, 2017. Saurav will be working full-time on a warehouse automation startup after his Ph.D.
Our heartiest congratulations to lab member Mohammadhussein Rafieisakhaei for successfully defending his Ph.D. Mohammad’s work focused on motion planning under uncertainty, particularly optimization-based methods. He will continue his research at TAMU.
Saurav Agarwal and Suman Chakravorty, members of the EDP Lab won the 2017 TechConnect National Innovation Award for the newly developed technology “A Method for Highly Accurate Long-Term Localization and Navigation Using On-Board Sensors.”
This innovation allows a system, such as a vehicle or robot, to navigate autonomously in previously unknown environments with less than a one-meter position error for 100 kilometers of motion without relying on GPS or any pre-built maps. The applications of this technology are immense and include military and commercial use, such as self-driving cars.
The TechConnect National Innovation Award selects the top early-stage innovations from around the world through an industry-review process of the top 20 percent of annually submitted technologies into the TechConnect National Innovation Summit. Rankings are based on the potential positive impact the submitted technology will have on a specific industry sector.
Our paper on a novel technique (RFM-SLAM) for 2D feature based SLAM has been accepted to ICRA 2017 to be held in Singapore!
The SLAM problem is known to have a special property that when robot orientation is known, estimating the history of robot poses and feature locations can be posed as a standard linear least squares problem. We have developed a SLAM framework that uses relative feature-to-feature measurements to exploit this structural property of SLAM. Relative feature measurements are used to pose a linear estimation problem for pose-to-pose orientation constraints. This is followed by solving an iterative non-linear on-manifold optimization problem to compute the maximum likelihood estimate for robot orientation given relative rotation constraints. Once the robot orientation is computed, we solve a linear problem for robot position and map estimation. Our approach reduces the computational burden of non-linear optimization by posing a smaller optimization problem as compared to standard graph-based methods for feature-based SLAM. By separating orientation estimation and formulating the robot and landmark position estimation as a linear least squares problem, no initial guess is required for the positions. Further, empirical results show our method avoids catastrophic failures that arise in existing methods due to using odometery as an initial guess for non-linear optimization, while its accuracy degrades gracefully as sensor noise is increased.
[Feel free to study the paper (pdf) submitted for review to ICRA 2017.]