Martin Servin - Academia.edu (original) (raw)

Papers by Martin Servin

Extraction of timber is expensive, energy intensive, and potentially damaging to the forest soil.... more Extraction of timber is expensive, energy intensive, and potentially damaging to the forest soil. Machine development aims to mitigate risks for environmental impact and decrease energy consumption while maintaining or increasing cost efficiency. Development of rubber-tracked forwarders have gained renewed interest, partly due to climate change leading to unreliable weather, and the urgency of reducing emissions. The increased cost of rubber-tracks compared to wheels are believed to be compensated by higher driving speeds and larger payloads. Thus, the aim of this study was to theoretically investigate how productivity and cost efficiency of rubber-tracked forwarders can exceed that of wheeled equivalents. The calculations were made with fixed parameters, to evaluate performance in different conditions, and with parameters from 2 500 final felling stands in central Sweden, to evaluate performance in varied working conditions. Scenarios were compared to a baseline corresponding to mi...

arXiv (Cornell University), Jun 19, 2023

We explore sim-to-real transfer of deep reinforcement learning controllers for a heavy vehicle wi... more We explore sim-to-real transfer of deep reinforcement learning controllers for a heavy vehicle with active suspensions designed for traversing rough terrain. While related research primarily focuses on lightweight robots with electric motors and fast actuation, this study uses a forestry vehicle with a complex hydraulic driveline and slow actuation. We simulate the vehicle using multibody dynamics and apply system identification to find an appropriate set of simulation parameters. We then train policies in simulation using various techniques to mitigate the sim-to-real gap, including domain randomization, action delays, and a reward penalty to encourage smooth control. In reality, the policies trained with action delays and a penalty for erratic actions perform nearly at the same level as in simulation. In experiments on level ground, the motion trajectories closely overlap when turning to either side, as well as in a route tracking scenario. When faced with a ramp that requires active use of the suspensions, the simulated and real motions are in close alignment. This shows that the actuator model together with system identification yield a sufficiently accurate model of the actuators. We observe that policies trained without the additional action penalty exhibit fast switching or bang-bang control. These present smooth motions and high performance in simulation but transfer poorly to reality. We find that policies make marginal use of the local height map for perception, showing no indications of look-ahead planning. However, the strong transfer capabilities entail that further development concerning perception and performance can be largely confined to simulation.

arXiv (Cornell University), Apr 19, 2021

Systems for transport and processing of granular media are challenging to analyse, operate and op... more Systems for transport and processing of granular media are challenging to analyse, operate and optimise. In the mining and mineral processing industries these systems are chains of processes with complex interplay between the equipment, control, and the processed material. The material properties have natural variations that are usually only known at certain locations. Therefore, we explore a material-oriented approach to digital twins with a particle representation of the granular media. In digital form, the material is treated as pseudo-particles, each representing a large collection of real particles of various sizes, shapes and, mineral properties. Movements and changes in the state of the material are determined by the combined data from control systems, sensors, vehicle telematics, and simulation models at locations where no real sensors can see. The particle-based representation enables material tracking along the chain of processes. Each digital particle can act as a carrier of observational data generated by the equipment as it interacts with the real material. This makes it possible to better learn material properties from process observations, and to predict the effect on downstream processes. We test the technique on a mining simulator and demonstrate analysis that can be performed using data from cross-system material tracking.

arXiv (Cornell University), Mar 3, 2021

Forestry machines are heavy vehicles performing complex manipulation tasks in unstructured produc... more Forestry machines are heavy vehicles performing complex manipulation tasks in unstructured production forest environments. Together with the complex dynamics of the on-board hydraulically actuated cranes, the rough forest terrains have posed a particular challenge in forestry automation. In this study, the feasibility of applying reinforcement learning control to forestry crane manipulators is investigated in a simulated environment. Our results show that it is possible to learn successful actuator-space control policies for energy efficient log grasping by invoking a simple curriculum in a deep reinforcement learning setup. Given the pose of the selected logs, our best control policy reaches a grasping success rate of 97%. Including an energy-optimization goal in the reward function, the energy consumption is significantly reduced compared to control policies learned without incentive for energy optimization, while the increase in cycle time is marginal. The energy-optimization effects can be observed in the overall smoother motion and acceleration profiles during crane manipulation.

Journal of Terramechanics, Apr 1, 2013

A new design for a tracked forestry machine bogie (Long Track Bogie; LTB) on soft and rough terra... more A new design for a tracked forestry machine bogie (Long Track Bogie; LTB) on soft and rough terrain is investigated using nonsmooth multibody dynamics simulation. The new bogie has a big wheel that is connected to and aligned with the chassis main axis. A bogie frame is mounted on the wheel axis but left to rotate freely up to a maximum angle and smaller wheels that also rotate freely are mounted on the frame legs with axes plane parallel to the driving wheel. The wheels are covered by a single conventional forestry machine metal track. The new bogie is shown to have higher mobility and cause less ground damage than a conventional tracked bogie but requires larger torque to create the same traction force as a conventional bogie. The new bogie also gives less acceleration when passing obstacles than the conventional bogie. Additionally, due to the shape and size of the new bogie concept, it can pass wider ditches.

arXiv (Cornell University), Mar 30, 2022

We present a method that uses high-resolution topography data of rough terrain, and ground vehicl... more We present a method that uses high-resolution topography data of rough terrain, and ground vehicle simulation, to predict traversability. Traversability is expressed as three independent measures: the ability to traverse the terrain at a target speed, energy consumption, and acceleration. The measures are continuous and reflect different objectives for planning that go beyond binary classification. A deep neural network is trained to predict the traversability measures from the local heightmap and target speed. To produce training data, we use an articulated vehicle with wheeled bogie suspensions and procedurally generated terrains. We evaluate the model on laser-scanned forest terrains, previously unseen by the model. The model predicts traversability with an accuracy of 90%. Predictions rely on features from the high-dimensional terrain data that surpass local roughness and slope relative to the heading. Correlations show that the three traversability measures are complementary to each other. With an inference speed 3000 times faster than the ground truth simulation and trivially parallelizable, the model is well suited for traversability analysis and optimal path planning over large areas.

arXiv (Cornell University), Sep 14, 2015

The effect on the convergence of warm starting the projected Gauss-Seidel solver for nonsmooth di... more The effect on the convergence of warm starting the projected Gauss-Seidel solver for nonsmooth discrete element simulation of granular matter are investigated. It is found that the computational performance can be increased by a factor 2 to 5.

arXiv (Cornell University), Mar 1, 2021

Reinforcement learning control of an underground loader is investigated in a simulated environmen... more Reinforcement learning control of an underground loader is investigated in a simulated environment, using a multi-agent deep neural network approach. At the start of each loading cycle, one agent selects the dig position from a depth camera image of the pile of fragmented rock. A second agent is responsible for continuous control of the vehicle, with the goal of filling the bucket at the selected loading point, while avoiding collisions, getting stuck, or losing ground traction. It relies on motion and force sensors, as well as on camera and lidar. Using a soft actor-critic algorithm, the agents learn policies for efficient bucket filling over many subsequent loading cycles, with clear ability to adapt to the changing environment. The best results, on average 75% of the max capacity, are obtained when including a penalty for energy usage in the reward.

arXiv (Cornell University), Dec 19, 2020

This paper presents a multi stage 3D shape reconstruction system of multiple object scenes by con... more This paper presents a multi stage 3D shape reconstruction system of multiple object scenes by considering the silhouette inconsistencies in shape-fromsilhouette SFS method. These inconsistencies are common in multiple view images due to object occlusions in different views, segmentation and shadows or reflection due to objects or light directions. These factors raise huge challenges when attempting to construct the 3D shape by using existing approaches which reconstruct only that part of the volume which projects consistently in all the silhouettes, leaving the rest unreconstructed. As a result, final shape are not robust due to multi view objects occlusion and shadows. In this regard, we consider the primary factors affecting reconstruction by analyzing the multiple images and perform pre-processing steps to optimize the silhouettes. Finally, the 3D shape is reconstructed by using the volumetric approach SFS. Theory and experimental results show that, the performance of the modified algorithm was efficiently improved, which can improve the accuracy of the reconstructed shape and being robust to errors in the silhouettes, volume and computational inexpensive.

The feasibility of using conditional GANs (Generative Adversarial Networks) to predict gripabilit... more The feasibility of using conditional GANs (Generative Adversarial Networks) to predict gripability in log piles is investigated. This is done by posing gripability heatmap prediction from RGB-D data as an image-to-image translation problem. Conditional GANs have previously achieved impressive results on several image-to-image translation tasks predicting physical properties and adding details not present in the input images. Here, piles of logs modelled as sticks or rods are generated in simulation, and groundtruth gripability maps are created using a simple algorithm streamlining the datacollection process. A modified SSIM (Structural Similarity Index) is used to evaluate the quality of the gripability heatmap predictions. The results indicate promising model performance on several different datasets and heatmap designs, including using base plane textures from a real forest production site to add realistic noise in the RGB data. Including a depth channel in the input data is shown...

Supplementary material 5 (mp4 36982 KB)

The discrete element method (DEM) is a versatile but computationally intense method for simulatio... more The discrete element method (DEM) is a versatile but computationally intense method for simulation of granular materials. It is therefore rarely used in applications that require realtime performance, e.g, interactive simulaions with a human operator or hardware in the loop. We investigate the use of reduced order modeling for achieving realtime performance in coupled discrete element and rigid multibody simulations. First, a large data set is produced from a series of simulations that cover a selected state-space. The particle data is coarse-grained into discrete field variables, representing mass density, velocity, strain and stress. A reduced order representation of the state-space is identified. Different methods for predicting the fields are explored, given certain observations and assumptions about the state of the simulation e.g., motion of boundaries, rigid bodies or control signals. The particle positions and velocities can then be advanced in time using the predicted field...

Supplementary material 8 (avi 51249 KB)

Supplementary material 1 (mp4 25758 KB)

Supplementary material 7 (avi 48851 KB)

Supplementary material 6 (mp4 45599 KB)

A deformable terrain model in multi-domain dynamics using elastoplastic constraints: An adaptive ... more A deformable terrain model in multi-domain dynamics using elastoplastic constraints: An adaptive approach Achieving realistic simulations of terrain vehicles in their work environment does not only require a careful model of the vehicle itself but the vehicle’s interactions with the surroundings are equally important. For off-road ground vehicles the terrain will heavily affect the behaviour of the vehicle and thus puts great demands on the terrain model. The purpose of this project has been to develop and evaluate a deformable terrain model, meant to be used in real-time simulations with multi-body dynamics. The proposed approach is a modification of an existing elastoplastic model based on linear elasticity theory and a capped Drucker-Prager model, using it in an adaptive way. The original model can be seen as a system of rigid bodies connected by elastoplastic constraints, representing the terrain. This project investigates if it is possible to create dynamic bodies just when it ...

In the present study we describe a mapping of existing terrain measurements [7] [8] [9] to the de... more In the present study we describe a mapping of existing terrain measurements [7] [8] [9] to the developed elastoplastic terrain model and numerical scheme. We also propose test system and procedures for parameter identification and for validation. The test systems include simple plate or cone tests as well as full vehicles equipped with industry standard wheels and tracked bogies. Finally, we present preliminary results from simulations of forestry machines with different type of tracked bogies.