Yashraj Narang

Yashraj Narang

Auto-generated profile, based on publicly available information

Yashraj Narang

NVIDIA, Santa Clara, CA, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
26 February 2018 in Advanced Functional Materials
Verified
Journal Article
Closed access
PDF file
YNYashraj S. Narang
Yashraj S. Narang
JVJoost J. Vlassak
Joost J. Vlassak
RHRobert D. Howe
Robert D. Howe

28 August 2019 in Advanced Materials Interfaces
Verified
Journal Article
Closed access
PDF file
SCSibo Cheng
Sibo Cheng
YNYashraj S. Narang
Yashraj S. Narang
CYCanhui Yang
Canhui Yang
ZSZhigang Suo
Zhigang Suo
RHRobert D. Howe
Robert D. Howe

4 December 2017 in IEEE Robotics and Automation Letters
Verified
Journal Article
Open access
YNYashraj S. Narang
Yashraj S. Narang
ADAlperen Degirmenci
Alperen Degirmenci
JVJoost J. Vlassak
Joost J. Vlassak
RHRobert D. Howe
Robert D. Howe
Researchers have developed variable-impedance mechanisms to control the dynamic response of robotic systems and improve their adaptivity, robustness, and efficiency. However, these mechanisms have limitations in size, cost, and convenience, particularly for variable damping. We demonstrate that laminar jamming structures can transform the dynamic response of robotic structures and systems while overcoming these limitations. In laminar jamming, an external pressure gradient is applied to a laminate of compliant material, changing its stiffness and damping. In this latter, we combine analysis, simulation, and characterization to formulate a lumped-parameter model that captures the nonlinear mechanical behavior of jamming structures and can be used to rapidly simulate their dynamic response. We illustrate that by adjusting the vacuum pressure, the fundamental features of the dynamic response (i.e., frequency, amplitude, decay rate, and steady-state value) can be tuned on command. Finally, we demonstrate that jamming structures can be integrated into soft structures and traditional rigid robots to considerably alter their response to impacts. With the models and demonstrations provided here, researchers may move further toward building versatile and transformative robots.

5 March 2025 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
IAIretiayo Akinola
Iretiayo Akinola
JXJie Xu
Jie Xu
JCJan Carius
Jan Carius
DFDieter Fox
Dieter Fox
YNYashraj Narang
Yashraj Narang
For both humans and robots,the sense of touch, known as tactile sensing, is critical for performing contact-rich manipulation tasks. Three key challenges in robotic tactile sensing are 1) interpreting sensor signals, 2) generating sensor signals in novel scenarios, and 3) learning sensor-based policies. For visuotactile sensors, interpretation has been facilitated by their close relationship with vision sensors (e.g., RGB cameras). However, generation is still difficult, as visuotactile sensors typically involve contact, deformation, illumination, and imaging, all of which are expensive to simulate; in turn, policy learning has been challenging, as simulation cannot be leveraged for large-scale data collection. We present TacSL (taxel), a library for GPU-based visuotactile sensor simulation and learning. TacSL can be used to simulate visuotactile images and extract contact-force distributions over $200\times$ faster than the prior state-of-the-art, all within the widely-used Isaac Simulator. Furthermore, TacSL provides a learning toolkit containing multiple sensor models, contact-intensive training environments, and online/offline algorithms that can facilitate policy learning for sim-to-real applications. On the algorithmic side, we introduce a novel online reinforcement-learning algorithm called asymmetric actor-critic distillation (AACD), designed to effectively and efficiently learn tactile-based policies in simulation that can transfer to the real world. Finally, we demonstrate the utility of our library and algorithms by evaluating the benefits of distillation and multimodal sensing for contact-rich manipulation tasks, and most critically, performing sim-to-real transfer. Supplementary videos and results are at https://iakinola23.github.io/tacsl/.

15 March 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
IHIsabella Huang
Isabella Huang
YNYashraj Narang
Yashraj Narang
CEClemens Eppner
Clemens Eppner
BSBalakumar Sundaralingam
Balakumar Sundaralingam
MMMiles Macklin
Miles Macklin
DFDieter Fox
Dieter Fox
Robotic grasping of 3D deformable objects (e.g., fruits/vegetables, internal organs, bottles/boxes) is critical for real-world applications such as food processing, robotic surgery, and household automation. However, developing grasp strategies for such objects is uniquely challenging. Unlike rigid objects, deformable objects have infinite degrees of freedom and require field quantities (e.g., deformation, stress) to fully define their state. As these quantities are not easily accessible in the real world, we propose studying interaction with deformable objects through physics-based simulation. As such, we simulate grasps on a wide range of 3D deformable objects using a GPU-based implementation of the corotational finite element method (FEM). To facilitate future research, we open-source our simulated dataset (34 objects, 1e5 Pa elasticity range, 6800 grasp evaluations, 1.1 M grasp measurements), as well as a code repository that allows researchers to run our full FEM-based grasp evaluation pipeline on arbitrary 3D object models of their choice. Finally, we demonstrate good correspondence between grasp outcomes on simulated objects and their real counterparts.

26 November 2021 in The International Journal of Robotics Research
Verified
Journal Article
Closed access
PDF file
YNYashraj S. Narang
Yashraj S. Narang
BSBalakumar Sundaralingam
Balakumar Sundaralingam
KWKarl Van Wyk
Karl Van Wyk
AMArsalan Mousavian
Arsalan Mousavian
DFDieter Fox
Dieter Fox
In the human hand, high-density contact information provided by afferent neurons is essential for many human grasping and manipulation capabilities. In contrast, robotic tactile sensors, including the state-of-the-art SynTouch BioTac, are typically used to provide low-density contact information, such as contact location, center of pressure, and net force. Although useful, these data do not convey or leverage the rich information content that some tactile sensors naturally measure. This research extends robotic tactile sensing beyond reduced-order models through (1) the automated creation of a precise experimental tactile dataset for the BioTac over a diverse range of physical interactions, (2) a 3D finite-element (FE) model of the BioTac, which complements the experimental dataset with high-density, distributed contact data, (3) neural-network-based mappings from raw BioTac signals to not only low-dimensional experimental data, but also high-density FE deformation fields, and (4) mappings from the FE deformation fields to the raw signals themselves. The high-density data streams can provide a far greater quantity of interpretable information for grasping and manipulation algorithms than previously accessible. Datasets, CAD files for the experimental testbed, FE model files, and videos are available at https://sites.google.com/nvidia.com/tactiledata .