Multi-log grasping using reinforcement learning and virtual visual servoing
Abstract: We explore multi-log grasping using reinforcement learning and virtual visual servoing for automated forwarding in a simulated environment. Automation of forest processes is a major challenge, and many techniques regarding robot control pose different challenges due to the unstructured and harsh outdoor environment. Grasping multiple logs involves various problems of dynamics and path planning, where understanding the interaction between the grapple, logs, terrain, and obstacles requires visual information. To address these challenges, we separate image segmentation from crane control and utilise a virtual camera to provide an image stream from reconstructed 3D data. We use Cartesian control to simplify domain transfer to real-world applications. Since log piles are static, visual servoing using a 3D reconstruction of the pile and its surroundings is equivalent to using real camera data until the point of grasping. This relaxes the limits on computational resources and time for the challenge of image segmentation and allows for collecting data in situations where the log piles are not occluded. The disadvantage is the lack of information during grasping. We demonstrate that this problem is manageable and present an agent that is 95% successful in picking one or several logs from challenging piles of 2--5 logs.
- “The economic potential of semi-automated tele-extraction of roundwood in Sweden” In International Journal of Forest Engineering 33.3 Taylor & Francis, 2022, pp. 271–288
- Peter Axelsson “Processing of laser scanner data—algorithms and applications” In ISPRS Journal of Photogrammetry and Remote Sensing 54.2, 1999, pp. 138–147 DOI: https://doi.org/10.1016/S0924-2716(99)00008-8
- “Terrain modelling and analysis using laser scanner data” In International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences 34.3/W4 NATURAL RESOURCES CANADA, 2001, pp. 219–226
- “Learning multiobjective rough terrain traversability” In Journal of Terramechanics 102 Elsevier, 2022, pp. 17–26
- “Advances in using robots in forestry operations” In Robotics and automation for improving agriculture Burleigh Dodds Science Publishing, 2019, pp. 233–260
- Shehan Caldera, Alexander Rassau and Douglas Chai “Review of deep learning methods in robotic grasp detection” In Multimodal Technologies and Interaction 2.3 MDPI, 2018, pp. 57
- “Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection” In The International journal of robotics research 37.4-5 SAGE Publications Sage UK: London, England, 2018, pp. 421–436
- “A survey on learning-based robotic grasping” In Current Robotics Reports 1 Springer, 2020, pp. 239–249
- “Increasing the level of automation in the forestry logging process with crane trajectory planning and control” In Journal of Field Robotics 31.3 Wiley Online Library, 2014, pp. 343–363
- “Nonlinear Model Learning for Compensation and Feedforward Control of Real-World Hydraulic Actuators Using Gaussian Processes” In IEEE Robotics and Automation Letters 7.4 IEEE, 2022, pp. 9525–9532
- “Reinforcement learning control of a forestry crane manipulator” In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021, pp. 2121–2126 IEEE
- Wenshuai Zhao, Jorge Peña Queralta and Tomi Westerlund “Sim-to-real transfer in deep reinforcement learning for robotics: a survey” In 2020 IEEE symposium series on computational intelligence (SSCI), 2020, pp. 737–744 IEEE
- “Sim-to-real transfer of active suspension control using deep reinforcement learning” In arXiv preprint arXiv:2306.11171, 2023
- “Autonomous Control of Redundant Hydraulic Manipulator Using Reinforcement Learning with Action Feedback” In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp. 7036–7043 IEEE
- “Semi-autonomous shared control of large-scale manipulator arms” In Control Engineering Practice 18.9 Elsevier, 2010, pp. 1069–1076
- “Depth-aware object segmentation and grasp detection for robotic picking tasks” In arXiv preprint arXiv:2111.11114, 2021
- “Instance segmentation for autonomous log grasping in forestry operations” In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp. 6064–6071 IEEE
- “Exploring the Feasibility of Autonomous Forestry Operations: Results from the First Experimental Unmanned Machine”, 2023
- Elie Ayoub, Patrick Levesque and Inna Sharf “Grasp Planning with CNN for Log-loading Forestry Machine” In 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023, pp. 11802–11808 IEEE
- Algoryx Simulations “AGX Dynamics”, 2023 URL: https://www.algoryx.se/products/agx-dynamics/
- Ken Perlin “An image synthesizer” In ACM Siggraph Computer Graphics 19.3 ACM New York, NY, USA, 1985, pp. 287–296
- Cranab AB “Forwarder Ccranes”, Brochure, 2015 URL: https://www.cranab.com/downloads/Forwarder-Cranes/Cranab-FC-brochure-EN.pdf
- Mark W Spong and Mathukumalli Vidyasagar “Robot dynamics and control” John Wiley & Sons, 2008
- “Patent WO2014118430A1”, https://patents.google.com/patent/WO2014118430A1/ko
- Richard S Sutton and Andrew G Barto “Reinforcement learning: An introduction” MIT press, 2018
- “Human-level control through deep reinforcement learning” In nature 518.7540 Nature Publishing Group, 2015, pp. 529–533
- “Stable-Baselines3: Reliable Reinforcement Learning Implementations” In Journal of Machine Learning Research 22.268, 2021, pp. 1–8
- “Proximal policy optimization algorithms” In arXiv preprint arXiv:1707.06347, 2017
- Stable baselines3 “PPO documentation”, 2023 URL: https://stable-baselines3.readthedocs.io/en/master/modules/ppo.html
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
