PythonRobotics: a Python code collection of robotics algorithms

Sakai, Atsushi; Ingram, Daniel J.; Dinius, J. D.; Chawla, Karan; Raffin, Antonin; Paques, Alexis

doi:10.48550/arxiv.1808.10703

Cited by 20 publications

(23 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…During inference, we unroll the waypoint generation module n times to get an n-step trajectory. We then fit a cubic spline on it using an existing framework provided by Sakai et al [30].…”

Section: Trajectory Interpolationmentioning

confidence: 99%

See 1 more Smart Citation

Learning Actions for Drift-Free Navigation in Highly Dynamic Scenes

Omama¹,

V.²,

Chinchali³

et al. 2021

Preprint

View full text Add to dashboard Cite

We embark on a hitherto unreported problem of an autonomous robot (self-driving car) navigating in dynamic scenes in a manner that reduces its localization error and eventual cumulative drift or Absolute Trajectory Error, which is pronounced in such dynamic scenes. With the hugely popular Velodyne-16 3D LIDAR as the main sensing modality, and the accurate LIDAR-based Localization and Mapping algorithm, LOAM, as the state estimation framework, we show that in the absence of a navigation policy, drift rapidly accumulates in the presence of moving objects. To overcome this, we learn actions that lead to drift-minimized navigation through a suitable set of reward and penalty functions. We use Proximal Policy Optimization, a class of Deep Reinforcement Learning methods, to learn the actions that result in drift-minimized trajectories. We show by extensive comparisons on a variety of synthetic, yet photo-realistic scenes made available through the CARLA Simulator the superior performance of the proposed framework vis-à-vis methods that do not adopt such policies.

show abstract

“…During inference, we unroll the waypoint generation module n times to get an n-step trajectory. We then fit a cubic spline on it using an existing framework provided by Sakai et al [30].…”

Section: Trajectory Interpolationmentioning

confidence: 99%

“…For this purpose we use a standard Stanley Controller [4], but it should be noted that our approach is invariant to the choice of the path tracking algorithm. The implementation of Stanley used is also provided by Sakai et al [30].…”

Section: Low-level Controlmentioning

confidence: 99%

Learning Actions for Drift-Free Navigation in Highly Dynamic Scenes

Omama¹,

V.²,

Chinchali³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The Tracker sees all agents in G.interior and guarantees no collisions by sending a brake signal when necessary to ensure a minimum safe distance is maintained at all times. The tracking algorithm that we use is an off-the-shelf MPC algorithm from [27].…”

Section: E Tracker Implementationmentioning

confidence: 99%

“…It will accomplish this while sending compatible inputs to the customer's car G (40) and not driving it into people and other cars G (41) . When the CustomerInterface sends a Retrieve command, the above process repeats with the Supervisor, which ensures that the last configuration is in the return area, thus satisfying G(27) . If this is the last sent path, then upon reaching the end of the path, it should notify the Planner module that it has completed the task by G (44) which satisfies A(24) , A (29) , and A (31) .The Supervisor alerts the CustomerInterface of the completed return by G(26) .…”

mentioning

confidence: 99%

Failure-Tolerant Contract-Based Design of an Automated Valet Parking System using a Directive-Response Architecture

Graebener,

Phan-Minh,

Yan

et al. 2021

Preprint

View full text Add to dashboard Cite

Increased complexity in cyber-physical systems calls for modular system design methodologies that guarantee correct and reliable behavior, both in normal operations and in the presence of failures. This paper aims to extend the contractbased design approach using a directive-response architecture to enable reactivity to failure scenarios. The architecture is demonstrated on a modular automated valet parking (AVP) system. The contracts for the different components in the AVP system are explicitly defined, implemented, and validated against a Python implementation.

show abstract

“…The algorithm was significantly affected by the data quality, however, it still worked well to determine whether a robot configuration belong to the free space. To reduce the processing time for the robot, RRT motion planning Karaman & Frazzoli (2011);Sakai et al (2018) was deployed in the robot. The two proposed frameworks are crucial portions to build an autonomous framework, which makes ARA robot implementing the tasks on the real steel bridge structure.…”

Section: Point Inside Boundary Check -Pibc and Path Planningmentioning

confidence: 99%

Control and Navigation Framework for a Hybrid Steel Bridge Inspection Robot

Bui,

2021

Preprint

View full text Add to dashboard Cite

Autonomous navigation of steel bridge inspection robots is essential for proper maintenance. Majority of existing robotic solutions for steel bridge inspection require human intervention to assist in the control and navigation. In this paper, a control and navigation framework has been proposed for the steel bridge inspection robot developed by the Advanced Robotics and Automation (ARA) to facilitate autonomous real-time navigation and minimize human intervention. The ARA robot is designed to work in two modes: mobile and inch-worm. The robot uses mobile mode when moving on a plane surface and inch-worm mode when jumping from one surface to the other. To allow the ARA robot to switch between mobile and inch-worm modes, a switching controller is developed with 3D point cloud data based. The surface detection algorithm is proposed to allow the robot to check the availability of steel surfaces (plane, area and height) to determine the transformation from mobile mode to inch-worm one. To have the robot to safely navigate and visit all steel members of the bridge, four algorithms are developed to process the data from a depth camera, segment it into clusters, estimate the boundaries, construct a graph representing the structure, generate the shortest inspection path with any starting and ending points, and determine available robot con-

show abstract

PythonRobotics: a Python code collection of robotics algorithms

Cited by 20 publications

References 2 publications

Learning Actions for Drift-Free Navigation in Highly Dynamic Scenes

Learning Actions for Drift-Free Navigation in Highly Dynamic Scenes

Failure-Tolerant Contract-Based Design of an Automated Valet Parking System using a Directive-Response Architecture

Control and Navigation Framework for a Hybrid Steel Bridge Inspection Robot

Contact Info

Product

Resources

About