Field test of neural-network based automatic bucket-filling algorithm for wheel-loaders

Dadhich, Siddharth; Sandin, Fredrik; Bodin, Ulf; Andersson, Ulf; Martinsson, Torbjörn

doi:10.1016/j.autcon.2018.10.013

Cited by 55 publications

(34 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Field experiments with a 14-tonne capacity load-haul-dump (LHD) machine and two types of excavation material (rock and gravel) revealed that the algorithm is able to achieve a target bucket fill weight within two to three excavation passes. Compared to AI-based approaches that require many training samples [5] and advanced computing hardware, the proposed controller has practical significance as demonstrated through these field experiments.…”

Section: Discussionmentioning

confidence: 99%

Iterative Learning-Based Admittance Control for Autonomous Excavation

Fernando

Marshall

Larsson

2019

J Intell Robot Syst

View full text Add to dashboard Cite

This paper presents the development and field validation of an iterative learning-based admittance control algorithm for autonomous excavation in fragmented rock using robotic wheel loaders. An admittance control strategy is augmented with iterative learning, which automatically updates control parameters based on the error between a target bucket fill weight and the measured fill weight at the end of each excavation pass. The algorithm was validated through full-scale autonomous excavation experiments with a 14-tonne capacity load-hauldump (LHD) machine and two different types of excavation materials: fragmented rock and gravel. In both excavation scenarios, the iterative learning algorithm is able to update the admittance control parameters for a specified target bucket fill weight, eliminating the need to manually re-tune control parameters as material

show abstract

Section: Discussionmentioning

confidence: 99%

Iterative Learning-Based Admittance Control for Autonomous Excavation

Fernando

Marshall

Larsson

2019

J Intell Robot Syst

View full text Add to dashboard Cite

show abstract

“…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]. This underscores the need for a generic automatic scooping solution that can be adapted to different scenarios.…”

Section: Related Workmentioning

confidence: 99%

“…One of the key challenges in deploying automated earth moving machines relates to the analysis of the soil-tool interaction, due to the unpredictable nature of the soil [6]. Most approaches require accurate models of the machine which makes them liable to modeling errors, wear and tear, and changing conditions [10]. Another drawback is that the majority of work done to automate scooping processes is based on data recorded by expert operators, which limits the efficiency to the level of the operator's skills [1].…”

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

“…A fully autonomous solution for robotic excavation must be able to identify and adapt to these variable conditions in order to achieve consistent bucket filling performance. Such a system would have obvious applications in construction [5], military [6], mining [7], and space exploration/development [8] where humans cannot be present for safety, logistical, and/or cost reasons.…”

Section: Introductionmentioning

confidence: 99%

What lies beneath: Material classification for autonomous excavators using proprioceptive force sensing and machine learning

Fernando

Marshall

2020

Automation in Construction

View full text Add to dashboard Cite

The ability of robotic excavators to acquire meaningful knowledge about materials during digging can augment their autonomous functionality, as well as optimize downstream operations in construction and mining. Some material properties, such as rock sizes, can be determined visually, but these methods cannot see what lies beneath. In this work, a classification methodology that utilizes only proprioceptive force data acquired from an autonomous digging system and machine learning algorithms is proposed for excavation material identification. The consistent performance synonymous with autonomous digging systems allows for the use of basic features extracted from the force data for classification. A proof of concept of this novel approach to excavation material classification is demonstrated through a binary classification of rock and gravel materials. Force data were obtained from full-scale autonomous loading trials with a 14-tonne capacity load-haul-dump machine at a mining and construction test facility. Preliminary results achieved a classification accuracy of 90 %.

show abstract

Field test of neural-network based automatic bucket-filling algorithm for wheel-loaders

Cited by 55 publications

References 19 publications

Iterative Learning-Based Admittance Control for Autonomous Excavation

Iterative Learning-Based Admittance Control for Autonomous Excavation

Wheel Loader Scooping Controller Using Deep Reinforcement Learning

What lies beneath: Material classification for autonomous excavators using proprioceptive force sensing and machine learning

Contact Info

Product

Resources

About