Umeå universitets logga

umu.sePublikationer
Ändra sökning
Länk till posten
Permanent länk

Direktlänk
Fälldin, Arvid
Publikationer (2 of 2) Visa alla publikationer
Aoshima, K., Fälldin, A., Wadbro, E. & Servin, M.Data-driven models for predicting the outcome of autonomous wheel loader operations.
Öppna denna publikation i ny flik eller fönster >>Data-driven models for predicting the outcome of autonomous wheel loader operations
(Engelska)Manuskript (preprint) (Övrigt vetenskapligt)
Abstract [en]

This paper presents a method using data-driven models for selecting actions and predicting the total performance of autonomous wheel loader operations over many loading cycles in a changing environment. The performance includes loaded mass, loading time, work. The data-driven models input the control parameters of a loading action and the heightmap of the initial pile state to output the inference of either the performance or the resulting pile state. By iteratively utilizing the resulting pile state as the initial pile state for consecutive predictions, the prediction method enables long-horizon forecasting. Deep neural networks were trained on data from over 10,000 random loading actions in gravel piles of different shapes using 3D multibody dynamics simulation. The models predict the performance and the resulting pile state with, on average, 95% accuracy in 1.2 ms, and 97% in 4.5 ms, respectively. The performance prediction was found to be even faster in exchange for accuracy by reducing the model size with the lower dimensional representation of the pile state using its slope and curvature. The feasibility of long-horizon predictions was confirmed with 40 sequential loading actions at a large pile. With the aid of a physics-based model, the pile state predictions are kept sufficiently accurate for longer-horizon use.

Nationell ämneskategori
Annan fysik Datorseende och robotik (autonoma system) Transportteknik och logistik Robotteknik och automation
Forskningsämne
fysik
Identifikatorer
urn:nbn:se:umu:diva-220410 (URN)10.48550/arXiv.2309.12016 (DOI)
Tillgänglig från: 2024-02-02 Skapad: 2024-02-02 Senast uppdaterad: 2024-02-05
Wiberg, V., Wallin, E., Fälldin, A., Semberg, T., Rossander, M., Wadbro, E. & Servin, M.Sim-to-real transfer of active suspension control using deep reinforcement learning.
Öppna denna publikation i ny flik eller fönster >>Sim-to-real transfer of active suspension control using deep reinforcement learning
Visa övriga...
(Engelska)Manuskript (preprint) (Övrigt vetenskapligt)
Abstract [en]

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 at nearly 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 yields 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. 

Nyckelord
autonomous vehicles, rough terrain navigation, machine learning, sim-to-real, reinforcement learning, heavy vehicles
Nationell ämneskategori
Datorseende och robotik (autonoma system) Annan fysik
Forskningsämne
fysik; data- och systemvetenskap
Identifikatorer
urn:nbn:se:umu:diva-207977 (URN)10.48550/arXiv.2306.11171 (DOI)
Forskningsfinansiär
Mistra - Stiftelsen för miljöstrategisk forskning, DIA 2017/14 #6
Tillgänglig från: 2023-05-05 Skapad: 2023-05-05 Senast uppdaterad: 2023-07-04Bibliografiskt granskad
Organisationer

Sök vidare i DiVA

Visa alla publikationer