| 1. |
- Bodin, Ulf, et al.
(author)
-
Remote Controlled Short-Cycle Loading of Bulk Material in Mining Applications
- 2015
-
In: IFAC-PapersOnLine. - : Elsevier. - 2405-8963. ; 48:17, s. 54-59
-
Journal article (peer-reviewed)abstract
- High-capacity wireless IP networks with limited delays are nowadays being deployed in both underground and open-pit mines. This allows for advanced remote control of mining machinery with improved feedback to operators and extensive monitoring of machine status, wear and fatigue. Wireless connectivity varies however depending on channel impairments caused by obstacles, multi-path fading and other radio issues. Therefore remote control and monitoring should be capable of adapting their sending rates to handle variations in communications quality. This paper presents key challenges in advanced remote control and monitoring of working machines via high-capacity wireless IP networks in mining environments. We reason about these challenges in context of underground short-cycle load, haul and dump operation with large-volume built wheel-loaders and present a generic communication solution for an operator assistance concept capable of adapting to varying communication properties
|
|
| 2. |
- Dadhich, Siddharth, 1987-, et al.
(author)
-
Adaptation of a wheel loader automatic bucket filling neural network using reinforcement learning
- 2020
-
In: 2020 International Joint Conference on Neural Networks (IJCNN). - : IEEE.
-
Conference paper (peer-reviewed)abstract
- Bucket-filling is a repetitive task in earth-moving operations with wheel-loaders, which needs to be automated to enable efficient remote control and autonomous operation. Ideally, an automated bucket-filling solution should work for different machine-pile environments, with a minimum of manual retraining. It has been shown that for a given machine-pile environment, a time-delay neural network can efficiently fill the bucket after imitation-based learning from 100 examples by one expert operator. Can such a bucket-filling network be automatically adapted to different machine-pile environments without further imitation learning by optimization of a utility or reward function? This paper investigates the use of a deterministic actor-critic reinforcement learning algorithm for automatic adaptation of a neural network in a new pile environment. The algorithm is used to automatically adapt a bucket-filling network for medium coarse gravel to a cobble-gravel pile environment. The experiments presented are performed with a Volvo L180H wheel-loader in a real-world setting. We found that the bucket-weights in the novel pile environment can improve by five to ten percent within one hour of reinforcement learning with less than 40 bucket-filling trials. This result was obtained after investigating two different reward functions motivated by domain knowledge.
|
|
| 3. |
|
|
| 4. |
- Dadhich, Siddharth, 1987-
(author)
-
Automation of Wheel-Loaders
- 2018
-
Doctoral thesis (other academic/artistic)abstract
- Automation and tele-remote operation of mobile earth moving machines is desired for safety and productivity reasons. With tele-operation and automation, operators can avoid harsh ergonomic conditions and hazardous environments with poor air quality, and the productivity can in principle be improved by saving the time required to commute to and from work areas. Tele-remote operation of a wheel-loader is investigated and compared with manual operation, and it is found that the constrained perception of the machine is a challenging problem with remote operations. Real-time video transmission over wireless is difficult, but presents a way towards improving the remote operator’s quality of experience. To avoid glitches in the real-time video, arising from variable wireless conditions, the use of SCReAM (Self-Clocked Rate Adaptation for Multimedia) protocol is proposed. Experiments with a small scale robot over LTE show the usefulness of SCReAM for time-critical remote control applications. Automation of the bucket-filling step in the loading cycle of a wheel-loader has been an open problem, despite three decades of research. To address the bucket-filling problem, imitation learning has been applied using expert operator data, experiments are performed with a 20-tonne Volvo L180H wheel-loader and an automatic bucket-filling solution is proposed, developed and demonstrated in field-tests. The conducted experiments are in the realm of small data (100 bucket-filling examples), shallow time-delayed neural-network (TDNN), and a wheel-loader interacting with a non-stationary pile-environment. The total delay length of the TDNN model is found to be an important hyperparameter, and the trained and tuned model comes close to the performance of an expert operator with slightly longer bucket-filling time. The proposed imitation learning trained on medium coarse gravel succeeds in filling buckets in a gravel cobble pile. However, a general solution for automatic bucket-filling needs to be adaptive to possible changes in operating conditions. To adapt an initial imitation model for unseen operating conditions, a reinforcement learning approach is proposed and evaluated. A deterministic actor-critic algorithm is used to update actor (control policy) and critic (policy evaluation) networks. The experiments show that by use of a carefully chosen reward signal the models learns to improve and maximizes bucket weights in a gravel-cobble pile with only 40 bucket-filling trials. This shows that an imitation learning based bucket-filling solution equipped with a reinforcement learning agent is well suited for the continually changing operating conditions found in the construction industry. The results presented in this thesis are a demonstration of the use of artificial intelligence and machine learning methods for the operation of construction equipment. Wheel-loader OEMs can use these results to develop an autonomous bucket-filling function that can be used in manual, tele-remote or fully autonomous operations.
|
|
| 5. |
- Dadhich, Siddharth, 1987-, et al.
(author)
-
Field test of neural-network based automatic bucket-filling algorithm for wheel-loaders
- 2019
-
In: Automation in Construction. - : Elsevier. - 0926-5805 .- 1872-7891. ; 97, s. 1-12
-
Journal article (peer-reviewed)abstract
- Automation of earth-moving industries (construction, mining and quarry) require automatic bucket-filling algorithms for efficient operation of front-end loaders. Autonomous bucket-filling is an open problem since three decades due to difficulties in developing useful earth models (soil, gravel and rock) for automatic control. Operators make use of vision, sound and vestibular feedback to perform the bucket-filling operation with high productivity and fuel efficiency. In this paper, field experiments with a small time-delayed neural network (TDNN) implemented in the bucket control-loop of a Volvo L180H front-end loader filling medium coarse gravel are presented. The total delay time parameter of the TDNN is found to be an important hyperparameter due to the variable delay present in the hydraulics of the wheel-loader. The TDNN network successfully performs the bucket-filling operation after an initial period (100 examples) of imitation learning from an expert operator. The demonstrated solution show only 26% longer bucket-filling time, an improvement over manual tele-operation performance.
|
|
| 6. |
- Dadhich, Siddharth, 1987-, et al.
(author)
-
From Tele-remote Operation to Semi-automated Wheel-loader
- 2018
-
In: International Journal of Electrical and Electronic Engineering and Telecommunications. - : International Journal of Electrical and Electronic Engineering & Telecommunications. - 2319-2518. ; 7:4, s. 178-182
-
Journal article (peer-reviewed)abstract
- This paper presents experimental results with tele-remote operation of a wheel-loader and proposes a method to semi-automate the process. The different components of the tele-remote setup are described in the paper. We focus on the short loading cycle, which is commonly used at quarry and construction sites for moving gravel from piles onto trucks. We present results from short-loading-cycle experiments with three operators, comparing productivity between tele-remote operation and manual operation. A productivity loss of 42% with tele-remote operation motivates the case for more automation. We propose a method to automate the bucket-filling process, which is one of the key operations performed by a wheel-loader.
|
|
| 7. |
- Dadhich, Siddharth, et al.
(author)
-
Key challenges in automation of earth-moving machines
- 2016
-
In: Automation in Construction. - : Elsevier BV. - 0926-5805 .- 1872-7891. ; 68, s. 212-222
-
Journal article (peer-reviewed)abstract
- A wheel loader is an earth-moving machine used in construction sites, gravel pits and mining to move blasted rock, soil and gravel. In the presence of a nearby dump truck, the wheel loader is said to be operating in a short loading cycle. This paper concerns the moving of material (soil, gravel and fragmented rock) by a wheel loader in a short loading cycle with more emphasis on the loading step. Due to the complexity of bucket-environment interactions, even three decades of research efforts towards automation of the bucket loading operation have not yet resulted in any fully autonomous system. This paper highlights the key challenges in automation and tele-remote operation of earth-moving machines and provides a survey of different areas of research within the scope of the earth-moving operation. The survey of publications presented in this paper is conducted with an aim to highlight the previous and ongoing research work in this field with an effort to strike a balance between recent and older publications. Another goal of the survey is to identify the research areas in which knowledge essential to automate the earth moving process is lagging behind. The paper concludes by identifying the knowledge gaps to give direction to future research in this field.
|
|
| 8. |
- Dadhich, Siddharth, et al.
(author)
-
Machine Learning approach to Automatic Bucket Loading
- 2016
-
In: 24th Mediterranean Conference on Control and Automation (MED). - Piscataway, NJ : IEEE Communications Society. - 9781467383455 ; , s. 1260-1265
-
Conference paper (peer-reviewed)abstract
- The automation of bucket loading for repetitive tasks of earth-moving operations is desired in several applications at mining sites, quarries and construction sites where larger amounts of gravel and fragmented rock are to be moved. In load and carry cycles the average bucket weight is the dominating performance parameter, while fuel efficiency and loading time also come into play with short loading cycles. This paper presents the analysis of data recorded during loading of different types of gravel piles with a Volvo L110G wheel loader. Regression models of lift and tilt actions are fitted to the behavior of an expert driver for a gravel pile. We present linear regression models for lift and tilt action that explain most of the variance in the recorded data and outline a learning approach for solving the automatic bucket loading problem. A general solution should provide good performance in terms of average bucket weight, cycle time of loading and fuel efficiency for different types of material and pile geometries. We propose that a reinforcement learning approach can be used to further refine models fitted to the behavior of expert drivers, and we briefly discuss the scooping problem in terms of a Markov decision process and possible value functions and policy iteration schemes.
|
|
| 9. |
- Arnrup, Kristina, et al.
(author)
-
A short-term follow-up of treatment outcome in groups of uncooperative child dental patients.
- 2004
-
In: European journal of paediatric dentistry : official journal of European Academy of Paediatric Dentistry. - 1591-996X. ; 5:4, s. 216-224
-
Journal article (peer-reviewed)abstract
- AIM: To evaluate the short-term follow-up outcome in four subgroups of uncooperative child dental patients referred to a specialist paediatric dental clinic in Sweden. METHODS: Seventy children, classified into four groups (based on fear, temperament, behaviour and verbal intelligence), were followed-up at their public dental clinics after termination of specialist dental treatment. Questionnaire assessments of children's dental and general fear, parental dental fear, emotional stress, locus of control and parenting efficacy were made by parents pre and post treatment and at follow-up and were analysed within and between groups. At follow-up, parents rated their children's coping and procedure stress, while treatment acceptance was rated by the dentists. RESULTS: Decreases in child dental fear were maintained at follow-up, although a third of children still had moderate or high dental fear. For those children who had been classified into the externalising, impulsive group, an increased risk of non-acceptance (RR=3.7) was indicated. The risk of dental fear at follow-up was increased for the group of fearful, inhibited children (RR=3.8). For the study group as a whole a poorer follow-up outcome could be predicted by avoidance behaviour (OR 12.9-16.6) and moderate or high post treatment dental fear (OR 6.5- 21.3). CONCLUSIONS: Fearful, inhibited child dental patients may need, due to dental fear, extra attention even after successful dental treatment at a specialist clinic. Externalising, impulsive children constitute a special challenge for dentistry. The continued need for adjusted management after termination of specialist treatment can be predicted from avoidance behaviour and post treatment dental fear scores.
|
|
| 10. |
- Arnrup, K, et al.
(author)
-
Classification of dental behavior management problems among children.
- 2007
-
In: Poster presentation at the 85th General Session & Exhibition of the IADR, New Orleans, LA, USA, March 21-24, 2007..
-
Conference paper (other academic/artistic)abstract
- Objectives: This study aimed to further investigate the heterogeneity within the group of children referred for specialist treatment because of dental behavior management problems (DBMP). A specific aim was to evaluate the validity of a previously reported cluster structure in another DBMP study group. Methods: 177 child dental patients, aged 4 to 12 at referral to a specialist pediatric dental clinic in Göteborg, Sweden, were classified into subgroups according to their personal characteristics. Cluster structure was described and compared to previously reported findings in a DBMP study group of same-aged child dental patients in Örebro, Sweden (n=74). Parental assessments of children's dental and general fear, temperament and behavior were made pre-treatment. The children also performed a vocabulary test. Data were analyzed mainly with a person-based approach using sequences of cluster analyses. Results: Classification into five different subgroups was judged the best representation of the Göteborg study group data, while four groups had been defined in Örebro. The new clusters partly paralleled the previous and were labeled (I) Extrovert, outgoing, (II) Highly fearful, multiple problems, (III) Highly fearful, (IV) Moderately fearful, externalizing, impulsive and (V) Moderately fearful, inhibited. Cluster profile II describes severe dental fear and general temperamental and behavioral problems of internalizing as well as externalizing character. Such combined problems were not clearly revealed in the Örebro cluster structure. Conclusion: The contention that children with dental behavior management problems (DBMP) comprise a heterogeneous group was strengthened. Similar, although not identical, clusters of children showing DBMP were identified in this replication study. Apart from different levels of dental fear, varying temperamental and behavioral characteristics need to be taken into consideration to better match treatment for these patients
|
|
