Rahul Batra
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Rahul Batra has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chaitanya Mehta
Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA
1 shared publication - Kelin Yu
Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA
1 shared publication - Nathan Boyd
Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA
1 shared publication - Seth Hutchinson
Northeastern University
1 shared publication - Tuo Zhao
Georgia Institute of Technology
1 shared publication - Ye Zhao
Georgia Institute of Technology
1 shared publication
Latest Publications
- Top Cited Papers
- 7 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 30 (1) , 554-566
Learning Generalizable Vision-Tactile Robotic Grasping Strategy for Deformable Objects via Transformer
Reliable robotic grasping, especially with deformable objects such as fruits, remains a challenging task due to underactuated contact interactions with a gripper, unknown object dynamics and geometries. In this study, we propose a transformer-based robotic grasping framework for rigid grippers that leverage tactile and visual information for safe object grasping. Specifically, the transformer models learn physical feature embeddings with sensor feedback through performing two predefined explorative actions (pinching and sliding) and predict a grasping outcome through a multilayer perceptron with a given grasping strength. Using these predictions, the gripper predicts a safe grasping strength via inference. Compared with convolutional recurrent networks, the transformer models can capture the long-term dependencies across the image sequences and process spatial–temporal features simultaneously. We first benchmark the transformer models on a public dataset for slip detection. Following that, we show that the transformer models outperform a CNN + LSTM model in terms of grasping accuracy and computational efficiency. We also collect a new fruit grasping dataset and conduct online grasping experiments using the proposed framework for both seen and unseen fruits. In addition, we extend our model to objects with different shapes and demonstrate the effectiveness of our pretrained model trained on our large-scale fruit dataset.
- 7 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 30 (1) , 554-566
Top Cited PapersLearning Generalizable Vision-Tactile Robotic Grasping Strategy for Deformable Objects via Transformer
Reliable robotic grasping, especially with deformable objects such as fruits, remains a challenging task due to underactuated contact interactions with a gripper, unknown object dynamics and geometries. In this study, we propose a transformer-based robotic grasping framework for rigid grippers that leverage tactile and visual information for safe object grasping. Specifically, the transformer models learn physical feature embeddings with sensor feedback through performing two predefined explorative actions (pinching and sliding) and predict a grasping outcome through a multilayer perceptron with a given grasping strength. Using these predictions, the gripper predicts a safe grasping strength via inference. Compared with convolutional recurrent networks, the transformer models can capture the long-term dependencies across the image sequences and process spatial–temporal features simultaneously. We first benchmark the transformer models on a public dataset for slip detection. Following that, we show that the transformer models outperform a CNN + LSTM model in terms of grasping accuracy and computational efficiency. We also collect a new fruit grasping dataset and conduct online grasping experiments using the proposed framework for both seen and unseen fruits. In addition, we extend our model to objects with different shapes and demonstrate the effectiveness of our pretrained model trained on our large-scale fruit dataset.