Obstacle avoidance for a hexapod robot in unknown environment

Chai, Xun; Gao, Feng; Qi, Chenkun; Pan, Yang; Xu, Yanling; Zhao, Yue

doi:10.1007/s11431-016-9017-6

Cited by 21 publications

(18 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, few works involve this process. Recently, Chai and Gao [69] presented a novel geometric feature grid map (GFGM) to describe the terrain for legged robots, which is useful for checking obstacles and finding paths in cluttered environments.…”

Section: Mappingmentioning

confidence: 99%

Mechanism, Actuation, Perception, and Control of Highly Dynamic Multilegged Robots: A Review

Gao

2020

Chin. J. Mech. Eng.

Self Cite

View full text Add to dashboard Cite

Multilegged robots have the potential to serve as assistants for humans, replacing them in performing dangerous, dull, or unclean tasks. However, they are still far from being sufficiently versatile and robust for many applications. This paper addresses key points that might yield breakthroughs for highly dynamic multilegged robots with the abilities of running (or jumping and hopping) and self-balancing. First, 21 typical multilegged robots from the last five years are surveyed, and the most impressive performances of these robots are presented. Second, current developments regarding key technologies of highly dynamic multilegged robots are reviewed in detail. The latest leg mechanisms with serial-parallel hybrid topologies and rigid–flexible coupling configurations are analyzed. Then, the development trends of three typical actuators, namely hydraulic, quasi-direct drive, and serial elastic actuators, are discussed. After that, the sensors and modeling methods used for perception are surveyed. Furthermore, this paper pays special attention to the review of control approaches since control is a great challenge for highly dynamic multilegged robots. Four dynamics-based control methods and two model-free control methods are described in detail. Third, key open topics of future research concerning the mechanism, actuation, perception, and control of highly dynamic multilegged robots are proposed. This paper reviews the state of the art development for multilegged robots, and discusses the future trend of multilegged robots.

show abstract

Section: Mappingmentioning

confidence: 99%

Mechanism, Actuation, Perception, and Control of Highly Dynamic Multilegged Robots: A Review

Gao

2020

Chin. J. Mech. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the navigation system, we are adopting pixy CMU cam5 image sensor in parallelism with the ultrasonic sensor, as image sensor solely doesn't read the data concerning the distance of the target from the vehicle. Consequently, with the use of the ultrasonic sensor, we wish to get the data of distance also (Chai et al, 2017, Lee et al, 2012, Al-Khatib et al, 2015, Cruz et al, 2011. Therefore applying both image sensor and ultrasonic we will have the precise information of a target, concerning its dimension, color and the distance of objects from the vehicle (Conte et al, 2002, Chen et al, 2015, Foresti, 2001).…”

Section: Autonomous Controlmentioning

confidence: 99%

Design and control of underwater hybrid vehicle capable of performing numerous tasks

Shahani¹,

Wei²,

Persaud³

et al. 2018

J. nav. arch. mar. engg.

View full text Add to dashboard Cite

This paper is about Ocean Strider; an Underwater Hybrid Vehicle that is modified with hybrid (manual and autonomous) control system. The aims concerning this Underwater Hybrid Vehicle are to be competent to operate underwater by using remote control via operator and seek out the user interested objects, and in case of autonomously to be smart, to visually follow and manage a secured position comparable to a motionless target, and to visually follow and move behind a moving target and avoid the hindrances for reliable navigation. Vision is a fundamental root that promotes the underwater robot to execute various tasks autonomously. Ocean Strider is intelligent to explicitly identify and locate objects by specifying from distinct color codes and dimension of the objects and respond accordingly. Multiple experiments have been conducted in the laboratory the robot successfully operates manually and grasp the objects underwater, and the robot can locate and track the objects autonomously, secure a fixed distance to the fixed object and travel onward with the object as it moves.

show abstract

“…Lower is betterAccuracy: higher is better Method Year Training pattern Cap (m) Abs Rel Sq Rel RMSE RMSE log δ < 1.25 1 δ < 1.25 δ < 1.253 Garg et al[23] L12 Aug8 × cap 50 m 2016…”

mentioning

confidence: 99%

Monocular depth estimation based on deep learning: An overview

Zhao¹,

Sun²,

Zhang³

et al. 2020

Sci. China Technol. Sci.

225

View full text Add to dashboard Cite

Depth information is important for autonomous systems to perceive environments and estimate their own state. Traditional depth estimation methods, like structure from motion and stereo vision matching, are built on feature correspondences of multiple viewpoints. Meanwhile, the predicted depth maps are sparse. Inferring depth information from a single image (monocular depth estimation) is an ill-posed problem. With the rapid development of deep neural networks, monocular depth estimation based on deep learning has been widely studied recently and achieved promising performance in accuracy. Meanwhile, dense depth maps are estimated from single images by deep neural networks in an end-to-end manner. In order to improve the accuracy of depth estimation, different kinds of network frameworks, loss functions and training strategies are proposed subsequently. Therefore, we survey the current monocular depth estimation methods based on deep learning in this review. Initially, we conclude several widely used datasets and evaluation indicators in deep learning-based depth estimation. Furthermore, we review some representative existing methods according to different training manners: supervised, unsupervised and semi-supervised. Finally, we discuss the challenges and provide some ideas for future researches in monocular depth estimation.

show abstract

Obstacle avoidance for a hexapod robot in unknown environment

Cited by 21 publications

References 21 publications

Mechanism, Actuation, Perception, and Control of Highly Dynamic Multilegged Robots: A Review

Mechanism, Actuation, Perception, and Control of Highly Dynamic Multilegged Robots: A Review

Design and control of underwater hybrid vehicle capable of performing numerous tasks

Monocular depth estimation based on deep learning: An overview

Contact Info

Product

Resources

About