Nikhil Potu Surya Prakash
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Nikhil Potu Surya Prakash has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Roberto Horowitz
Department of Mechanical Engineering, University of California, Berkeley, USA
2 shared publications - Changhao Wang
University of California, Berkeley, CA, USA
1 shared publication - Jongeun Choi
School of Mechanical Engineering, Yonsei University, Seoul, Republic of Korea
1 shared publication - Joohwan Seo
School of Mechanical Engineering, Yonsei University, Seoul, Republic of Korea
1 shared publication - Masayoshi Tomizuka
UC Berkeley
1 shared publication - Xiang Zhang
Department of Mechanical Engineering, University of California, Berkeley, CA, USA
1 shared publication
Latest Publications
- Open Access
- 18 March 2025
- Published by Qeios Ltd
Review of: "What’s the Move? Hybrid Imitation Learning via Salient Points"
The paper presents SPHINX (Salient Point-Based Hybrid ImitatioN and eXecution), a hybrid imitation learning (IL) approach for robot manipulation tasks. SPHINX effectively combines multimodal observations—point clouds for long-range waypoints and wris...
- 18 March 2025
- Published by Qeios Ltd
Open AccessReview of: "What’s the Move? Hybrid Imitation Learning via Salient Points"
The paper presents SPHINX (Salient Point-Based Hybrid ImitatioN and eXecution), a hybrid imitation learning (IL) approach for robot manipulation tasks. SPHINX effectively combines multimodal observations—point clouds for long-range waypoints and wris...
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (2) , 1508-1515
Contact-Rich SE(3)-Equivariant Robot Manipulation Task Learning via Geometric Impedance Control
This letter presents a differential geometric control approach that leverages SE(3) group invariance and equivariance to increase transferability in learning robot manipulation tasks that involve interaction with the environment. Specifically, we employ a control law and a learning representation framework that remain invariant under arbitrary SE(3) transformations of the manipulation task definition. Furthermore, the control law and learning representation framework are shown to be SE(3) equivariant when represented relative to the spatial frame. The proposed approach is based on utilizing a recently presented geometric impedance control (GIC) combined with a learning variable impedance control framework, where the gain scheduling policy is trained in a supervised learning fashion from expert demonstrations. A geometrically consistent error vector (GCEV) is fed to a neural network to achieve a gain scheduling policy that remains invariant to arbitrary translation and rotations. A comparison of our proposed control and learning framework with a well-known Cartesian space learning impedance control, equipped with a Cartesian error vector-based gain scheduling policy, confirms the significantly superior learning transferability of our proposed approach. A hardware implementation on a peg-in-hole task is conducted to validate the learning transferability and feasibility of the proposed approach.
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (2) , 1508-1515
Contact-Rich SE(3)-Equivariant Robot Manipulation Task Learning via Geometric Impedance Control
This letter presents a differential geometric control approach that leverages SE(3) group invariance and equivariance to increase transferability in learning robot manipulation tasks that involve interaction with the environment. Specifically, we employ a control law and a learning representation framework that remain invariant under arbitrary SE(3) transformations of the manipulation task definition. Furthermore, the control law and learning representation framework are shown to be SE(3) equivariant when represented relative to the spatial frame. The proposed approach is based on utilizing a recently presented geometric impedance control (GIC) combined with a learning variable impedance control framework, where the gain scheduling policy is trained in a supervised learning fashion from expert demonstrations. A geometrically consistent error vector (GCEV) is fed to a neural network to achieve a gain scheduling policy that remains invariant to arbitrary translation and rotations. A comparison of our proposed control and learning framework with a well-known Cartesian space learning impedance control, equipped with a Cartesian error vector-based gain scheduling policy, confirms the significantly superior learning transferability of our proposed approach. A hardware implementation on a peg-in-hole task is conducted to validate the learning transferability and feasibility of the proposed approach.
- Open Access
- 8 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3949-3954
Data-Driven Strictly Positive Real System Identification with prior System Knowledge
Strictly Positive Real (SPR) transfer functions arise in many areas of engineering like passivity theory in circuit analysis and adaptive control to name a few. In many physical systems, it is possible to conclude that the system is Positive Real (PR) or SPR but system identification algorithms might produce estimates which are not SPR. In this paper, a convex optimization algorithm to approximate frequency response data with SPR transfer functions using Generalized Orthonormal Basis Functions (GOBFs) is presented. Prior knowledge of the system helps us to get approximate pole locations, which can then be used to construct GOBFs.
- 8 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3949-3954
Open AccessData-Driven Strictly Positive Real System Identification with prior System Knowledge
Strictly Positive Real (SPR) transfer functions arise in many areas of engineering like passivity theory in circuit analysis and adaptive control to name a few. In many physical systems, it is possible to conclude that the system is Positive Real (PR) or SPR but system identification algorithms might produce estimates which are not SPR. In this paper, a convex optimization algorithm to approximate frequency response data with SPR transfer functions using Generalized Orthonormal Basis Functions (GOBFs) is presented. Prior knowledge of the system helps us to get approximate pole locations, which can then be used to construct GOBFs.