Torbjörn Martinsson - Academia.edu (original) (raw)
I'm developing AI in mobile robotics aiming for productivity as humans.
less
Uploads
Papers by Torbjörn Martinsson
La presente invention concerne un systeme (18) permettant de determiner une entite de materiau (3... more La presente invention concerne un systeme (18) permettant de determiner une entite de materiau (32) a eliminer d'un pieu (16) au moyen d'un outil (12) d'un engin de deplacement de materiau (10). Le systeme (18) comprend des moyens de generation d'une forme actuelle de pieu (26) de la forme de surface reelle du pieu (16). De plus, le systeme (18) est concu pour determiner une forme nominale de pieu (28) d'au moins une partie du pieu (16). La forme nominale de pieu (28) est determinee sur la base d'au moins la forme actuelle de pieu (26) et d'informations concernant le type de materiau du pieu (16). En outre, ledit systeme (18) est concu pour determiner un volume excedentaire (30) entre la forme nominale de pieu (28) et la forme actuelle de pieu (26) et le systeme (18) est concu pour determiner l'entite de materiau (32) a eliminer du pieu (16) sur la base du volume excedentaire (30).
Automation in Construction, 2019
Automation of earth-moving industries (construction, mining and quarry) require automatic bucket-... more 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.
2020 International Joint Conference on Neural Networks (IJCNN), 2020
Bucket-filling is a repetitive task in earth-moving operations with wheel-loaders, which needs to... more 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 experime...
La presente invention concerne un systeme (18) permettant de determiner une entite de materiau (3... more La presente invention concerne un systeme (18) permettant de determiner une entite de materiau (32) a eliminer d'un pieu (16) au moyen d'un outil (12) d'un engin de deplacement de materiau (10). Le systeme (18) comprend des moyens de generation d'une forme actuelle de pieu (26) de la forme de surface reelle du pieu (16). De plus, le systeme (18) est concu pour determiner une forme nominale de pieu (28) d'au moins une partie du pieu (16). La forme nominale de pieu (28) est determinee sur la base d'au moins la forme actuelle de pieu (26) et d'informations concernant le type de materiau du pieu (16). En outre, ledit systeme (18) est concu pour determiner un volume excedentaire (30) entre la forme nominale de pieu (28) et la forme actuelle de pieu (26) et le systeme (18) est concu pour determiner l'entite de materiau (32) a eliminer du pieu (16) sur la base du volume excedentaire (30).
Automation in Construction, 2019
Automation of earth-moving industries (construction, mining and quarry) require automatic bucket-... more 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.
2020 International Joint Conference on Neural Networks (IJCNN), 2020
Bucket-filling is a repetitive task in earth-moving operations with wheel-loaders, which needs to... more 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 experime...