[CSIRO RAS Seminar] Agriculture Robotics and Adaptive Grasping

Share

CSIRO's Robotics and Autonomous Systems Group is hosting Prof. Michael Wang and Dr. Chao Chen from Monash University for a combined seminar on agriculture robotics and adaptive grasping.

[Michael Yu Wang] Adaptive Grasping with Touch Sensing and Dry-Adhesive Contact

Abstract: In the field of robotic manipulation, touch sensing and contact adhesion have been considered as essential techniques for versatile capabilities of adaptive grasping and manipulation. Thanks to respective advances in optical tactile sensors and in scalable fabrication of gecko-inspired dry adhesive skins, these distinctive techniques continue to be developed. Moreover, complementary sense of touch and adaptive contact can be integrated into a robotic gripper. As such, touch sensing is endowed into a gecko-gripper for the promise of adaptive grasping.

In this presentation, I will review our work on optical touch sensing and adhesive contact skins. Our deformable sensor provides high-resolution real-time measurements of contact area and contact shear force. Gecko-inspired dry-adhesive skins are readily integrated on the sensor surface, providing variable adhesion and friction. I will showcase the gripper’s ability to adjust fingertip pose for better contact using sensor feedback, especially for top-side gripping onto a nearly flat surface (smooth or rough) of an object with firm attachment. I will show practical applications in industrial automation and discuss the recent developments throughout the robotics community advancing in this promising direction.

Bio: Michael Yu Wang is a Professor and the Head of Department of Mechanical and Aerospace Engineering of Monash University. Before joining Monash University in 2022, he was the Founding Director of HKUST’s Cheng Kar-Chun Robotics Institute. He also served on the engineering faculty at University of Maryland, Chinese University of Hong Kong, and National University of Singapore. He has numerous professional honors–Kayamori Best Paper Award of 2001 IEEE International Conference on Robotics and Automation, the Compliant Mechanisms Award-Theory of ASME 31st Mechanisms and Robotics Conference in 2007, Research Excellence Award (2008) of CUHK, and ASME Design Automation Award (2013). He is the current Editor-in-Chief of IEEE Trans. on Automation Science and Engineering, and served as an Associate Editor of IEEE Trans. on Robotics and Automation and ASME Journal of Manufacturing Science and Engineering. He is a Fellow of ASME, HKIE and IEEE. He received his Ph.D. degree from Carnegie Mellon University.  

 

[Chao Chen] The Monash Apple Retrieving System (MARS)

 Abstract: Farmers and fruit growers have acknowledged the need to adopt smart technologies and automation on their farms to combat the growing concern of manual labour shortages, with estimated losses of over $38 million per year attributed to unharvested crops in Australia. Selective harvesting of high value crops such as fruits and vegetables is a very labour-intensive and expensive task, which makes it a good candidate for robotic automation. This need has driven significant research and investments in automated harvesting robots recently, leading to advancements in vision and fruit detection algorithms, innovative robot designs, and fruit extraction mechanisms. However, adoption of these robots among farmers remains low, due to significant technical challenges in handling complex canopy environments.

In this presentation, I will introduce our apple harvesting robot developed in my laboratory LMGA, called the Monash Apple Retrieving System (MARS) which can harvest up to 8 apples per minute in complex yet typical canopy environments. The robot features a six degree of freedom robotic arm for dexterous harvesting, a vision system capable of real time detection of apples in an occluded environment, and soft gripper to extract difficult-to-reach fruit from within the canopy without damage. The system is integrated with fruit pose estimation and intelligent planning algorithms to optimise harvesting performance. Our technologies and algorithms allow MARS to harvest non-destructively with high precision, which will appeal to many local farmers who are concerned about significant canopy damage that can be caused by robotic harvesters.

Bio: Chao Chen is a Senior Lecturer in the Department of Mechanical and Aerospace Engineering of Monash University. He is also an Adjunct Associate Professor at the Chinese University of Hong Kong. He established the Laboratory of Motion Generation and Analysis and is the founding academic and supervisor of Monash Nova Rover Team. He received the 2022 Award of Editor’s Choice Article by Sensors, the 2020 Superior Paper Award by Computers and Electronics in Agriculture, and the 2017 Innovation Award by Australian Hand Therapy Association. His Nova Rover Team achieved the 2nd Place in University Rover Challenge at Mars Desert Research Station in Utah in 2022. He is currently the Editor of Agronomy: Precision and Digital Agriculture. He received his Ph.D. degree from McGill University.



  Date and Time

  Location

  Hosts

  Registration



  • Date: 01 Jul 2022
  • Time: 11:00 AM to 12:00 PM
  • All times are (UTC+10:00) Brisbane
  • Add_To_Calendar_icon Add Event to Calendar
If you are not a robot, please complete the ReCAPTCHA to display virtual attendance info.
  • Co-sponsored by CSIRO's Robotics and Autonomous Systems Group
  • Starts 21 June 2022 02:49 PM
  • Ends 01 July 2022 11:30 AM
  • All times are (UTC+10:00) Brisbane
  • No Admission Charge


  Speakers

Michael Wang of Monash University

Topic:

Adaptive Grasping with Touch Sensing and Dry-Adhesive Contact

In the field of robotic manipulation, touch sensing and contact adhesion have been considered as essential techniques for versatile capabilities of adaptive grasping and manipulation. Thanks to respective advances in optical tactile sensors and in scalable fabrication of gecko-inspired dry adhesive skins, these distinctive techniques continue to be developed. Moreover, complementary sense of touch and adaptive contact can be integrated into a robotic gripper. As such, touch sensing is endowed into a gecko-gripper for the promise of adaptive grasping.

In this presentation, I will review our work on optical touch sensing and adhesive contact skins. Our deformable sensor provides high-resolution real-time measurements of contact area and contact shear force. Gecko-inspired dry-adhesive skins are readily integrated on the sensor surface, providing variable adhesion and friction. I will showcase the gripper’s ability to adjust fingertip pose for better contact using sensor feedback, especially for top-side gripping onto a nearly flat surface (smooth or rough) of an object with firm attachment. I will show practical applications in industrial automation and discuss the recent developments throughout the robotics community advancing in this promising direction.

Biography:

Michael Yu Wang is a Professor and the Head of Department of Mechanical and Aerospace Engineering of Monash University. Before joining Monash University in 2022, he was the Founding Director of HKUST’s Cheng Kar-Chun Robotics Institute. He also served on the engineering faculty at University of Maryland, Chinese University of Hong Kong, and National University of Singapore. He has numerous professional honors–Kayamori Best Paper Award of 2001 IEEE International Conference on Robotics and Automation, the Compliant Mechanisms Award-Theory of ASME 31st Mechanisms and Robotics Conference in 2007, Research Excellence Award (2008) of CUHK, and ASME Design Automation Award (2013). He is the current Editor-in-Chief of IEEE Trans. on Automation Science and Engineering, and served as an Associate Editor of IEEE Trans. on Robotics and Automation and ASME Journal of Manufacturing Science and Engineering. He is a Fellow of ASME, HKIE and IEEE. He received his Ph.D. degree from Carnegie Mellon University.  

 

Monash University

Topic:

The Monash Apple Retrieving System (MARS)

Farmers and fruit growers have acknowledged the need to adopt smart technologies and automation on their farms to combat the growing concern of manual labour shortages, with estimated losses of over $38 million per year attributed to unharvested crops in Australia. Selective harvesting of high value crops such as fruits and vegetables is a very labour-intensive and expensive task, which makes it a good candidate for robotic automation. This need has driven significant research and investments in automated harvesting robots recently, leading to advancements in vision and fruit detection algorithms, innovative robot designs, and fruit extraction mechanisms. However, adoption of these robots among farmers remains low, due to significant technical challenges in handling complex canopy environments.

In this presentation, I will introduce our apple harvesting robot developed in my laboratory LMGA, called the Monash Apple Retrieving System (MARS) which can harvest up to 8 apples per minute in complex yet typical canopy environments. The robot features a six degree of freedom robotic arm for dexterous harvesting, a vision system capable of real time detection of apples in an occluded environment, and soft gripper to extract difficult-to-reach fruit from within the canopy without damage. The system is integrated with fruit pose estimation and intelligent planning algorithms to optimise harvesting performance. Our technologies and algorithms allow MARS to harvest non-destructively with high precision, which will appeal to many local farmers who are concerned about significant canopy damage that can be caused by robotic harvesters.

Biography:

Chao Chen is a Senior Lecturer in the Department of Mechanical and Aerospace Engineering of Monash University. He is also an Adjunct Associate Professor at the Chinese University of Hong Kong. He established the Laboratory of Motion Generation and Analysis and is the founding academic and supervisor of Monash Nova Rover Team. He received the 2022 Award of Editor’s Choice Article by Sensors, the 2020 Superior Paper Award by Computers and Electronics in Agriculture, and the 2017 Innovation Award by Australian Hand Therapy Association. His Nova Rover Team achieved the 2nd Place in University Rover Challenge at Mars Desert Research Station in Utah in 2022. He is currently the Editor of Agronomy: Precision and Digital Agriculture. He received his Ph.D. degree from McGill University.