Modelling of robotic bulldozing operations for autonomous control

Olsen, Scott G.; Bone, Gary M.

doi:10.1109/ccece.2011.6030650

Cited by 8 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One explanation may be the complexity of this task. Specifically, the actual operation of dozers requires skillful operators as the behavior of the soil is irreversible [3].…”

Section: A Bulldozer Automationmentioning

confidence: 99%

Towards Autonomous Grading In The Real World

Miron¹,

Ross²,

Goldfracht³

et al. 2022

Preprint

View full text Add to dashboard Cite

Fig. 1. A comparison of grading policy between a simulated dozer and a real world scaled prototype on an area containing sand piles. Here, the agent is provided with an initial graded area and is required to extend it by pushing newly added sand piles. Top Row: Photos of our experimental setup (see Section IV-A) showing the scaled dozer prototype facing the sand piles. Middle & Bottom Rows: Heightmaps extracted from our simulation and scaled experimental setup respectively. Sand piles are captured as dark blobs that indicate their height. Each column compares the grading policy in the experimental setup and the simulation on a similar scenario.

show abstract

“…One explanation may be the complexity of this task. Specifically, the actual operation of dozers requires skillful operators as the behavior of the soil is irreversible [3].…”

Section: A Bulldozer Automationmentioning

confidence: 99%

Towards Autonomous Grading In The Real World

Miron¹,

Ross²,

Goldfracht³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…These compliance control methods do not follow a desired trajectory but rather apply specific forces to the pile during the scooping motion. The third category is made up of control algorithms that employ a behavior-based approach for motion control, such as a rule-based algorithm that depends on the current phase and acts dynamically [8], [9]. Thus, most previous solutions to automate the scooping task (1) do not generalize to different machines or pile environments (2) rely on prior knowledge of an expert operator and (3) require accurate models of the machine and therefore are susceptible to failure in the presence of modeling errors, wear and tear, and changing conditions [10].…”

Section: Related Workmentioning

confidence: 99%

“…Designing control methods for such tasks is a long-standing research goal, which has attracted considerable interest and generated a number of survey papers [2], [3]. The general approaches to autonomous excavation exploit the machine dynamics and try to follow a defined trajectory [4], [5], use compliance force control [6], [7] or employ a behavior-based approach for motion control [8], [9]. Since some tasks are more complex than others, they often require extensive engineering experience and tedious manual tuning beyond the control algorithm itself.…”

Section: Introductionmentioning

confidence: 99%

Wheel Loader Scooping Controller Using Deep Reinforcement Learning

Azulay

Shapiro

2021

IEEE Access

View full text Add to dashboard Cite

This article presents a deep reinforcement learning-based controller for an unmanned ground vehicle with a custom-built scooping mechanism. The robot's aim is to autonomously perform earth scooping cycles with three degrees of freedom: lift, tilt and the robot's velocity. While the majority of previous studies on automated scooping processes are based on data recorded by expert operators, we present a method to autonomously control a wheel loader to perform the scooping cycle using deep reinforcement learning methods without any user-provided demonstrations. The controller's learning approach is based on the actorcritic, Deep Deterministic Policy Gradient algorithm which we use to map online sensor data as input to continuously update the actuator commands. The training of the scooping policy network is done solely in a simplified simulation environment using a virtual physics engine, which converges to an average of a 65% fill factor from the full bucket capacity and a 5 [ ] average cycle time. We illustrate the performance of the trained policy in simulations and in real-world experiments with 3 different inclination angles of the earth. An additional scooping experiment compared the performance of our controller to remote manual human control. Overall, the deep reinforcement learning-based controller exhibited good performance in terms of both achieved visually bucket fill with varying scooped earth weights of 4.1 − 7.2[ ], and a 5.1 − 7.1[ ] cycle time. The experimental results confirm the ability of our planner to fill bucket as required, indicating that our controller can be used for excavation purposes.

show abstract

“…At TRL 3-5, Olsen and Bone [60] investigated the modelling of a robotic bulldozing operation for the purpose of autonomous control. Later, in [61], the bulldozer's workflow was modelled using an adaptive neural network to simulate and predict the dependence of the resistance strain of gauge bogie displacement on the dig depth and trolley speed in dynamics.…”

Section: Principles and Subsystemsmentioning

confidence: 99%

Earthmoving Construction Automation with Military Applications: Past, Present and Future

Ha¹,

Yen²,

Balaguer³

2018

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

Amongst increasing innovations in frontier engineering sciences, the advancements in Robotic and Autonomous Systems (RAS) has brought about a new horizon in construction applications. There is evidence of increasing interest in RAS technologies in the civil construction sector being reflected in construction efforts of many military forces. In particular, Army or ground-based military forces are frequently called upon to conduct construction tasks as part of military operations, tasks which could be partially or fully aided by the employment of RAS technologies. Along with recent advances in the Internet of Things (IoT) and cyberphysical system infrastructure, it is essential to examine the current technical feasibility, maturity, affordability, as well as the challenges and future directions of the adoption and application of RAS to military construction. This paper presents a comprehensive survey and provides a contemporary and industry-independent overview on the state-ofthe-art of construction automation used in defence, spanning current world's best practice through to that which is predicted over the coming years.

show abstract

Modelling of robotic bulldozing operations for autonomous control

Cited by 8 publications

References 7 publications

Towards Autonomous Grading In The Real World

Towards Autonomous Grading In The Real World

Wheel Loader Scooping Controller Using Deep Reinforcement Learning

Earthmoving Construction Automation with Military Applications: Past, Present and Future

Contact Info

Product

Resources

About