Learning Behavior Trees From Demonstration

French, Kevin; Wu, S. M.; Pan, Tianyang; Zhou, Zebing; Jenkins, Odest Chadwicke

doi:10.1109/icra.2019.8794104

Cited by 60 publications

(29 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge there are only three previous studies [4]- [6] that combine LfD and BTs. The method proposed in [4] and [5] learns a mapping from state space to action space as a Decision Tree (DT), which is converted into a BT, using the fact that BTs generalize DTs [7]. In [6], on the other hand, authors encode the demonstrated sequence of actions directly as a BT.…”

Section: Related Workmentioning

confidence: 99%

“…The final BT, however, cannot be used as is but requires a final tuning of parameters, thus limiting its usage to support the final NPC design. This is extended by [5] who generalize it to use any logic minimizer instead of the greedy algorithm, and implement the solution on a mobile manipulator performing a house cleaning task. The whole action space and state space are encoded in the tree which would then contain elements that are not used at runtime and complicate the structure of the BT.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Combining Context Awareness and Planning to Learn Behavior Trees from Demonstration

Gustavsson¹,

Iovino²,

Styrud³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fast changing tasks in unpredictable, collaborative environments are typical for medium-small companies, where robotised applications are increasing. Thus, robot programs should be generated in short time with small effort, and the robot able to react dynamically to the environment. To address this we propose a method that combines context awareness and planning to learn Behavior Trees (BTs), a reactive policy representation that is becoming more popular in robotics and has been used successfully in many collaborative scenarios. Context awareness allows to infer from the demonstration the frames in which actions are executed and to capture relevant aspects of the task, while a planner is used to automatically generate the BT from the sequence of actions from the demonstration. The learned BT is shown to solve non-trivial manipulation tasks where learning the context is fundamental to achieve the goal. Moreover, we collected non-expert demonstrations to study the performances of the algorithm in industrial scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Combining Context Awareness and Planning to Learn Behavior Trees from Demonstration

Gustavsson¹,

Iovino²,

Styrud³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…BTs are used for drone inspection in congested traffic environments in [9] and completed trial runs at the Clifton Suspension Bridge. Other applications include multi agent underwater robots [10] and mobile manipulators for picking [11] and cleaning households [12].…”

Section: Related Work a Behavior Trees(bts)mentioning

confidence: 99%

A Persistent and Context-aware Behavior Tree Framework for Multi Sensor Localization in Autonomous Driving

Yi¹,

Nebot²

2021

Preprint

View full text Add to dashboard Cite

Fig. 1. Vehicle trajectories of 53 rosbags in the University of Sydney Campus Dataset output from the GPS+lidar main filter are superimposed together onto a satellite image. No manual alignment of trajectory is performed. The color of trajectory points indicates the state of update used by the filter. Green: lidar feature updating. Blue: dead reckoning. Red: GPS updating. The blue dead reckoning area in the middle of the image is an underground carpark.

show abstract

“…Robotic System Papers Manipulators [100], [4], [139], [59], [123], [124], [125], [24], [30], [35], [22], [9] Mobile Manipulators [23], [26], [27], [22], [138], [50], [73], [82], [147], [54], [182] Wheeled Robots [153], [154], [6], [1], [2], [96] Robot Swarms [87], [76], [77], [106], [107], [171] Humanoid Robots [30], [9], [101], [164], [64], [33] Autonomous vehicles [28], [115] Aerial Robots [83], [84], [85], [86], [145], [89], [19],...…”

Section: Tablementioning

confidence: 99%