Duckietown: An open, inexpensive and flexible platform for autonomy education and research

Paull, Liam; Tani, Jacopo; Ahn, Heejin; Alonso–Mora, Javier; Carlone, Luca; Ćáp, Michal; Chen, Yu Fan; Choi, Changhyun; Dusek, Jeff; Fang, Yajun; Hoehener, Daniel; Liu, Shih‐Yuan; Novitzky, Michael; Okuyama, Igor Franzoni; Pazis, Jason; Rosman, Guy; Varricchio, Valerio; Wang, Hsueh‐Cheng; Yershov, Dmitry S.; Zhao, Hang; Benjamin, Michael R.; Carr, Christopher E.; Zuber, M. T.; Karaman, Sertaç; Frazzoli, Emilio; Vecchio, Domitilla Del; Rus, Daniela; How, Jonathan P.; Leonard, John J.; Censi, Andrea

doi:10.1109/icra.2017.7989179

Cited by 168 publications

(86 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The closest effort to this [16] trains grasping policies for low-cost mobile manipulators by collecting data from several such manipulators under varying lighting conditions. Finally, previous efforts have also provided standardized and easily accessible full hardware stacks such as Duckietown for navigation [28] and Robotarium for swarm robotics [29]. We share their motivation of democratizing robotics and driving increased participation, and our focus is on manipulation tasks.…”

Section: Related Workmentioning

confidence: 99%

REPLAB: A Reproducible Low-Cost Arm Benchmark for Robotic Learning

Yang

Jayaraman

Zhang

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Standardized evaluation measures have aided in the progress of machine learning approaches in disciplines such as computer vision and machine translation. In this paper, we make the case that robotic learning would also benefit from benchmarking, and present the "REPLAB" platform for benchmarking vision-based manipulation tasks. REPLAB is a reproducible and self-contained hardware stack (robot arm, camera, and workspace) that costs about 2000 USD, occupies a cuboid of size 70x40x60 cm, and permits full assembly within a few hours. Through this low-cost, compact design, REPLAB aims to drive wide participation by lowering the barrier to entry into robotics and to enable easy scaling to many robots. We envision REPLAB as a framework for reproducible research across manipulation tasks, and as a step in this direction, we define a template for a grasping benchmark consisting of a task definition, evaluation protocol, performance measures, and a dataset of 92k grasp attempts. We implement, evaluate, and analyze several previously proposed grasping approaches to establish baselines for this benchmark. Finally, we also implement and evaluate a deep reinforcement learning approach for 3D reaching tasks on our REPLAB platform. Project page with assembly instructions, code, and videos: https://goo.gl/5F9dP4.

show abstract

Section: Related Workmentioning

confidence: 99%

REPLAB: A Reproducible Low-Cost Arm Benchmark for Robotic Learning

Yang

Jayaraman

Zhang

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…• Provide baseline implementations of algorithms commonly used in both ML (e.g., reinforcement learning, imitation learning) and robotics (see Paull et al [20] for details) communities;…”

Section: The Software Infrastructurementioning

confidence: 99%

“…While the finals of AI-DO 1 proved to be a good demonstration that the simulator-reality gap is large, we did not have a metric for quantifying it. The Duckietown codebase has had a working lane following solution since 2016 [20], so we know that a robust solution to the LF challenge was feasible. However, in simulation this robust solution did not perform well.…”

Section: Simulationmentioning

confidence: 99%

See 1 more Smart Citation

The AI Driving Olympics at NeurIPS 2018

Zilly

Tani

Considine

et al. 2019

The NeurIPS '18 Competition

Self Cite

View full text Add to dashboard Cite

Despite recent breakthroughs, the ability of deep learning and reinforcement learning to outperform traditional approaches to control physically embodied robotic agents remains largely unproven. To help bridge this gap, we created the "AI Driving Olympics" (AI-DO), a competition with the objective of evaluating the state of the art in machine learning and artificial intelligence for mobile robotics. Based on the simple and well specified autonomous driving and navigation environment called "Duckietown," AI-DO includes a series of tasks of increasing complexity -from simple lane-following to fleet management. For each task, we provide tools for competitors to use in the form of simulators, logs, code templates, baseline implementations and low-cost access to robotic hardware. We evaluate submissions in simulation online, on standardized hardware environments, and finally at the competition event. The first AI-DO, AI-DO 1, occurred at the Neural Information Processing Systems (NeurIPS) conference in December 2018. The results of AI-DO 1 highlight the need for better benchmarks, which are lacking in robotics, as well as improved mechanisms to bridge the gap between simulation and reality.

show abstract

“…A standardized platform is also existing for the RoboCup soccer scenario [7] which led to the development of approaches for the platforms limited in computing power. More recently, Paull et al [8] presented Duckietown, an open research platform for miniature autonomous driving tasks. Duckietown consists of Duckiebots, which are the autonomous robots themselves, driving around in Duckietown.…”

Section: Related Workmentioning

confidence: 99%

Scratchy: A Lightweight Modular Autonomous Robot for Robotic Competitions

Memmesheimer

Kuhlmann

Mints

et al. 2019

2019 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

View full text Add to dashboard Cite

We present Scratchy-a modular, lightweight robot built for low budget competition attendances. Its base is mainly built with standard 4040 aluminium profiles and the robot is driven by four mecanum wheels on brushless DC motors. In combination with a laser range finder we use estimated odometry -which is calculated by encoders -for creating maps using a particle filter. A RGB-D camera is utilized for object detection and pose estimation. Additionally, there is the option to use a 6-DOF arm to grip objects from an estimated pose or generally for manipulation tasks. The robot can be assembled in less than one hour and fits into two pieces of hand luggage or one bigger suitcase. Therefore, it provides a huge advantage for student teams that participate in robot competitions like the European Robotics League or RoboCup. Thus, this keeps the funding required for participation, which is often a big hurdle for student teams to overcome, low. The software and additional hardware descriptions are available under: https://github.com/homer-robotics/scratchy.

show abstract

Duckietown: An open, inexpensive and flexible platform for autonomy education and research

Cited by 168 publications

References 14 publications

REPLAB: A Reproducible Low-Cost Arm Benchmark for Robotic Learning

REPLAB: A Reproducible Low-Cost Arm Benchmark for Robotic Learning

The AI Driving Olympics at NeurIPS 2018

Scratchy: A Lightweight Modular Autonomous Robot for Robotic Competitions

Contact Info

Product

Resources

About