Shubham Vyas

Shubham Vyas

Auto-generated profile, based on publicly available information

Shubham Vyas

Robotics Innovation Center, German Research Center for Artificial Intelligence, Bremen, Germany

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 December 2023 in IEEE Robotics & Automation Magazine
Verified
Journal Article
Open access
FWFelix Wiebe
Felix Wiebe
SKShivesh Kumar
Shivesh Kumar
LSLasse J. Shala
Lasse J. Shala
SVShubham Vyas
Shubham Vyas
MJMahdi Javadi
Mahdi Javadi
FKFrank Kirchner
Frank Kirchner
Recent interest in the control of underactuated robots has surged significantly due to the impressive athletic behaviors shown by robots developed by, e.g., Boston Dynamics ( https://www.bostondynamics.com ), Agility Robotics ( https://agilityrobotics.com/robots ), and the Massachusetts Institute of Technology [1]. This gives rise to the need for canonical robotic hardware setups for studying underactuation and comparing learning and control algorithms for their performance and robustness. Similar to OpenAIGym [2] and Stable Baselines [3], which provide simulated benchmarking environments and baselines for reinforcement learning algorithms, there is a need for benchmarking learning and control methods on real canonical hardware setups. To encourage reproducibility in robotics and artificial intelligence research, these hardware setups should be affordable and easy to manufacture with off-the-shelf components, and the accompanying software should be open source. Acrobots and pendubots are classical textbook examples of canonical underactuated systems with strong nonlinear dynamics, and their swing-up and upright balancing is considered a challenging control problem, especially on real hardware.

21 April 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
MJMahdi Javadi
Mahdi Javadi
DHDaniel Harnack
Daniel Harnack
PSPaula Stocco
Paula Stocco
SKShivesh Kumar
Shivesh Kumar
SVShubham Vyas
Shubham Vyas
FKFrank Kirchner
Frank Kirchner
Brachiation is a dynamic, coordinated swinging maneuver of body and arms used by monkeys and apes to move between branches. As a unique underactuated mode of locomotion, it is interesting to study from a robotics perspective since it can broaden the deployment scenarios for humanoids and animaloids. While several brachiating robots of varying complexity have been proposed in the past, this letter presents the simplest possible prototype of a brachiation robot, using only a single actuator and unactuated grippers. The novel passive gripper design allows it to snap on and release from monkey bars, while guaranteeing well defined start and end poses of the swing. The brachiation behavior is realized in three different ways, using trajectory optimization via direct collocation and stabilization by a model-based time-varying linear quadratic regulator (TVLQR) or model-free proportional derivative (PD) control, as well as by a reinforcement learning (RL) based control policy. The three control schemes are compared in terms of robustness to disturbances, mass uncertainty, and energy consumption. The system design and controllers have been open-sourced. Due to its minimal and open design, the system can serve as a canonical underactuated platform for education and research.

15 December 2025 in IEEE Robotics & Automation Magazine
Verified
Journal Article
Open access
FWFelix Wiebe
Felix Wiebe
NTNiccolò Turcato
Niccolò Turcato
ALAlberto Dalla Libera
Alberto Dalla Libera
JCJean Seong Bjorn Choe
Jean Seong Bjorn Choe
BCBumkyu Choi
Bumkyu Choi
SKShivesh Kumar
Shivesh Kumar
In robotics, many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. To get a clear understanding of their individual strengths and weaknesses and their applicability in real-world robotic scenarios, it is important to benchmark and compare their performances not only in a simulation but also on real hardware. The second AI Olympics with RealAIGym competition was held at the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024) to contribute to this cause and evaluate different controllers according to their ability to solve a dynamic control problem on an underactuated double-pendulum system (Figure 1) with chaotic dynamics. This article describes the four different RL methods submitted by the participating teams; presents their performance in the swing-up task on a real double pendulum, measured against various criteria; and discusses their transferability from simulation to real (sim-to-real) hardware and their robustness to external disturbances.

2 July 2015
Verified
Conference Paper
Open access
FJFrancis James
Francis James
SVShubham Vyas
Shubham Vyas
PBPuneeth Bandikatla
Puneeth Bandikatla
PMP. Mithun
P. Mithun
SSS. V. Shah
S. V. Shah
In space robots, coupling between the base and the arms causes the floating base to translate and rotate when the arms execute a maneuver, which is typically not seen in earth based robots. Since it is difficult to test developments in space robotics primarily due to the high cost and lack of access to robots in space, it is necessary to have physical systems that can mimic space conditions for experimental validation on earth. Among several options, the use of air bearings to build floating-base robots is one of the most effective. We describe the development of one such system that replicates zero gravity conditions for planar robots. Although similar systems exist elsewhere, the planar dual-arm space robot we have built is distinctive by being relatively lightweight, compact and modular. The setup can be used to test a wide range of experiments such as visual servoing, reactionless maneuvering and object grasping in space. In this paper, the approach taken during the development of both the hardware and software for the experimental setup are discussed. A few results obtained by numerical simulations as well as experimentation are also presented.

19 August 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
MAMaximilian Albracht
Maximilian Albracht
SKShivesh Kumar
Shivesh Kumar
SVShubham Vyas
Shubham Vyas
FKFrank Kirchner
Frank Kirchner
A great advantage of legged robots is their ability to operate on particularly difficult and obstructed terrain, which demands dynamic, robust, and precise movements. The study of obstacle courses provides invaluable insights into the challenges legged robots face, offering a controlled environment to assess and enhance their capabilities. Traversing it with a one-legged hopper introduces intricate challenges, such as planning over contacts and dealing with flight phases, which necessitates a sophisticated controller. A novel model predictive parkour controller is introduced, that finds an optimal path through a real-time changing obstacle course with mixed integer motion planning. The execution of this optimized path is then achieved through a state machine employing a PD control scheme with feedforward torques, ensuring robust and accurate performance.

17 October 2022 in Journal of Space Safety Engineering
Verified
Journal Article
Closed access
SVShubham Vyas
Shubham Vyas
MJMarko Jankovic
Marko Jankovic
FKFrank Kirchner
Frank Kirchner