Abhisesh Silwal
Senior Project Scientist | Carnegie Mellon University
Pittsburgh, PA, UNITED STATES
Abhisesh Silwal's research interest is in end-to-end robotic systems tailored for complex outdoor environments.
Biography
Abhisesh Silwal's research interest is in end-to-end robotic systems tailored for complex outdoor environments, synthesizing cutting-edge research across various branches of robotics to address real-world challenges. This often leads to proof-of-concept robotic systems that demonstrate novel concepts to do things that have never been done before. His particular interest is in agriculture, where he is fascinated not only by the complexity and challenges it presents to robotics, but also the societal benefit it offers through technological advancements. He focuses on full-autonomy stack, pioneering novel sensing methodologies, modular robot design principles, and the creation of low-cost, rugged systems customized to specific application needs.
Areas of Expertise (8)
Field Robotics
Robots for Education
Reinforcement Learning
Human Robot Collaboration
3-D Vision and Recognition
Deep Learning
RoboEthics
Control Theory
Media Appearances (3)
AI and the future of agriculture
IBM online
2024-09-24
Dr. Abhisesh Silwal, a systems scientist at Carnegie Mellon University whose research focuses on AI and robotics in agriculture, thinks so. “AI could lead to more accurate and timely predictions, especially for spotting diseases early,” he explains, “and it could help cut down on carbon footprints and environmental impact by improving how we use energy and resources.”
Ag researchers learning how to teach a robot
Good Fruit Grower online
2024-08-22
Abhisesh Silwal, a CMU Robotics Institute scientist, said they’re currently using AI technology to teach robots the way humans prune, via a teleoperation system that collects human demonstration data. He said industry-standard, human-centric pruning rules are difficult for robots to follow. Robots must be able to identify canopy parts such as trunks, canes, buds and cordons, and they must know where cuts need to be made. So, the simpler the canopy, the better.
We’re one step closer to self-farming farms
Vox online
2022-01-08
“Similar to the autonomous car industry, full autonomy of farm vehicles and equipment can also be considered as an important, if not the ultimate, goal in the agriculture industry,” said Abhisesh Silwal, a project scientist who works on agricultural robots at Carnegie Mellon University’s Robotics Institute. He added that automating delicate, time-sensitive tasks like pruning and harvesting, which typically require skilled workers, could help sustainability in the long run.
Media
Publications:
Documents:
Videos:
Audio/Podcasts:
Industry Expertise (2)
Agriculture and Farming
Mechanical/Industrial Engineering
Education (2)
Washington State University: Ph.D. 2016
Asian Institute of Technology: M.S. 2012
Links (3)
Event Appearances (1)
EDT RISS Robolaunch
July 2024 Online
Patents (1)
Robotic systems, methods, and end-effectors for harvesting produce
US9554512B2
2017 Robotic systems and specialized end-effectors provide for automated harvesting of produce such as fresh market apples. An underactuated design using tendons and flexure joints with passive compliance increases robustness to position error, overcoming a significant limitation of previous fruit harvesting end-effectors. Some devices use open-loop control, provide a shape-adaptive grasp, and produce contact forces similar to those used during optimal hand picking patterns. Other benefits include relatively low weight, low cost, and simplicity.
Articles (3)
Semantics-guided skeletonization of upright fruiting offshoot trees for robotic pruning
Computers and Electronics in Agriculture2022 Dormant pruning for fresh market fruit trees is a relatively unexplored application of agricultural robotics for which few end-to-end systems exist. One of the biggest challenges in creating an autonomous pruning system is the need to reconstruct a model of a tree which is accurate and informative enough to be useful for deciding where to cut. One useful structure for modeling a tree is a skeleton: a 1D, lightweight representation of the geometry and the topology of a tree. This skeletonization problem is an important one within the field of computer graphics, and a number of algorithms have been specifically developed for the task of modeling trees. These skeletonization algorithms have largely addressed the problem as a geometric one. In agricultural contexts, however, the parts of the tree have distinct labels, such as the trunk, supporting branches, etc.
Advanced Learning and Classification Techniques for Agricultural and Field Robotics
Fundamentals of Agricultural and Field Robotics2021 Today, increasingly a large number of growers are utilizing smart agricultural tools as a daily part of their precision agricultural strategy to improve overall crop health and get the most out of their fields while optimizing resource utilization. With the advent of low-cost sensors and internet of things, more data is available within the agricultural industry than ever. Several industries including manufacturing, financial, and service industries have used AI-powered analytics to gain unparalleled edge by extracting valuable information from bigdata to improve product value and sales, boost marketing, and to predict future trends in real time. In recent years, agricultural industries have also started to adopt and apply AI-based solutions for various cumbersome tasks. Advanced learning and classification are some of the fundamental analytical tools used to make decision using large amount of data.
Apple crop-load estimation with over-the-row machine vision system
Computers and Electronics in Agriculture2016 Accurate crop-load estimation is important for efficient management of pre- and post-harvest operations. This information is crucial for the planning of labor and equipment requirement for harvesting and transporting fruit from the orchard to packing house. Current machine vision-based techniques for crop-load estimation have achieved only limited success mostly due to: (i) occlusion of apples by branches, leaves and/or other apples, and (ii) variable outdoor lighting conditions. In order to minimize the effect of these factors, a new sensor system was developed with an over-the-row platform integrated with a tunnel structure which acquired images from opposite sides of apple trees. The tunnel structure minimized illumination of apples with direct sunlight and reduced the variability in lighting condition.
Social