no code implementations • 20 Apr 2023 • Yin Yong Chee, Parham Oveissi, Siyuan Shao, Joonghyun Lee, Juan A. Paredes, Dennis S. Bernstein, Ankit Goel
This paper modifies an adaptive multicopter autopilot to mitigate instabilities caused by adaptive parameter drift and presents simulation and experimental results to validate the modified autopilot.
no code implementations • 26 Nov 2022 • Turibius Rozario, Arjun Trivedi, Ankit Goel
Specifically, we develop neural networks as a composition of several vector-valued functions.
no code implementations • 24 Oct 2022 • Joonghyun Lee, John Spencer, Siyuan Shao, Juan Augusto Paredes, Dennis S. Bernstein, Ankit Goel
Next, the performance of the adaptive autopilot is examined under failure conditions by simulating a scenario where one of the control surfaces is assumed to be stuck at an unknown angle.
no code implementations • 18 Aug 2022 • Ankit Goel, Dennis S. Bernstein
The most accurate version of the unscented Kalman filter (UKF) involves the construction of two ensembles.
no code implementations • 15 Aug 2022 • Ankit Goel, Dennis S. Bernstein
This technique, called retrospective cost parameter estimation (RCPE), is motivated by large-scale complex estimation models characterized by high-dimensional nonlinear dynamics, nonlinear parameterizations, and representational models.
no code implementations • 21 Oct 2021 • Joonghyun Lee, John Spencer, Juan Augusto Paredes, Sai Ravela, Dennis S. Bernstein, Ankit Goel
This paper develops an adaptive digital autopilot for a fixed-wing aircraft and compares its performance with a fixed-gain autopilot.
no code implementations • 27 Sep 2021 • John Spencer, Joonghyun Lee, Juan Augusto Paredes, Ankit Goel, Dennis Bernstein
This paper develops an adaptive PID autotuner for multicopters, and presents simulation and experimental results.
no code implementations • 1 Apr 2021 • Ankit Goel, Dennis S. Bernstein
The ultimate goal is thus to develop modifications of UKF that specialize to the Kalman filter for linear systems and have improved accuracy for nonlinear systems.