Context Speakers Program Challenge Accepted papers Organizers Contact Return To Top

Context

Precision agriculture techniques are essential for increasing crop yields while reducing environmental impact, particularly in the face of climate change effects. Commercial robotic solutions are actively being deployed to assist in agricultural tasks. However, autonomous robots are far from reaching their full potential in this domain. Fully autonomous robots can significantly impact precision agriculture by providing mapping, sensing, or manipulation capabilities for crops and forests, enabling fruit counting, tree diameter estimation, crop disease detection, carbon sequestration quantification, smart spraying, and biomass estimation, among others.

This workshop bridges industry and academia to discuss how to close the gap towards autonomous robots in agricultural and field robotics settings. Key topics include innovative forestry techniques for tree diameter and biomass estimation, datasets, semantic simultaneous localization and mapping (SLAM), motion planning and navigation in cluttered environments, crop inspections, and applications. Attendees will gain insights into the latest research and developments at the intersection of precision agriculture and robotics from academic and industrial perspectives, as well as the open challenges in the field and novel approaches to tackling them.

This workshop will also provide a forum for researchers beyond the agricultural robotics community to learn about this field, encouraging them to apply their expertise in this challenging domain.

Speakers

Program

Time Speaker / Session Talk Title Recording
9:00 Opening Remarks - -
9:15 Frank Dellaert Sensing, thinking, and acting in the service of superhuman farming -
9:35 Katie Driggs-Campbell On the Roles of Humans in Human-Agbot Teams: Refining, Monitoring, and Supervising -
9:55 David Cappelleri P-AgBot: An autonomous mobile robot for in-row and under-canopy monitoring, assessment, and physical sampling -
10:05 Poster & Coffee Break - -
10:40 Stefano Carpin Hands off programming of mobile robots in precision agriculture Link
11:00 Jim Ostrowski Off the Road to Autonomy: Bringing Autonomous Tractors to Production in Agriculture -
11:20 Guillermo Pita Gil Demo time is over: why the ugly 20% hurts… and pays! -
11:40 Panel 1 - -
12:10 Lunch - -
13:10 Cosimo Della Santina Grasping with (Soft) Hands in Agriculture -
13:30 Tim Barfoot Towards Reliable Offroad Navigation Using Radar Link
13:50 Lightning Talks - -
14:50 Poster & Coffee Break - -
15:20 Max Tubman Wildland Fire Management and Avalanche Mitigation with Drones -
15:40 Steven Chen Robotics and Machine Learning for Vegetation Management -
16:00 Kostas Karydis Odometry Estimation, Mapping, and Multi-modal Scene Understanding for Autonomous Agricultural Mobile Robots -
16:20 Panel 2 - -
16:50 Closing Remarks Awards for best paper and Treescope challenge -

Tree diameter estimation challenge

The Novel Approaches for Precision Agriculture and Forestry with Autonomous Robots Workshop is hosting a tree diameter estimation based on the Treescope dataset. Participants are requested to estimate tree diameter at breast height (DBH) in a provided point cloud. We will award $150 to the most accurate submission.

This challenge is an excellent opportunity for both seasoned and entry-level researchers in robotics forestry. Do not miss the chance to submit!

Important: you need to submit a one to two page description of your approach and your code in CMT if you want your submission to be considered for the award.

Challenge website: https://www.codabench.org/competitions/7343/

Key dates

  • April 14 - Submissions open for the development phase
  • May 16 - Submissions open for the testing phase
  • May 21 - Participants are required to submit a description of their approach in CMT. Deadline 11.59 pm AoE.
  • May 23 - The challenge winner will be announced at the workshop.

Accepted papers

Title arXiv ID
Tactile Perception-Based Quantitative Hardness Assessment for Fruit Classification and Grasping 2505.05725
Parameter-Efficient Fine-Tuning of Vision Foundation Model for Forest Floor Segmentation from UAV Imagery 2505.08932
Mapping Semantic Segmentation to Point Clouds Using Structure from Motion for Forest Analysis 2505.10751
Fast Heuristic Scheduling and Trajectory Planning for Robotic Fruit Harvesters with Multiple Cartesian Arms 2505.10028
A drone that learns to efficiently find objects in agricultural fields: from simulation to the real world 2505.09278
Ground robot navigation in dense forests with 3D LiDAR using Reinforcement Learning -
Lightweight Multispectral Crop-Weed Segmentation for Precision Agriculture 2505.07444
Estimating the Diameter at Breast Height of Trees in a Forest With a Single 360° Camera 2505.03093
LiDAR-Based Canopy Volume Estimation for Orchard Trees -
Robotic Monitoring of Colorimetric Leaf Sensors for Precision Agriculture 2505.13916
Geofenced Unmanned Aerial Robotic Defender for Deer Detection and Deterrence (GUARD) 2505.10770
Robust 2D lidar-based SLAM in arboreal environments without IMU/GNSS 2505.10847
GrowSplat: Constructing Temporal Digital Twins of Plants with Gaussian Splats 2505.10923

Contact

Do not hesitate to write us for any questions:

 fclad [at] seas.upenn.edu

Acknowledgement

We would like to acknowledge the Agricultural Robotics and Automation TC for funding the best paper award of the workshop.

The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.

This website was built with Hugo and the Hugo Scroll template.