Structure augmented monocular saliency for planetary rovers

Spiteri, Conrad; Shaukat, Affan; Gao, Yang

doi:10.1016/j.robot.2016.11.013

Cited by 3 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the results produced are better than local methods. Local methods are simpler but only provide an approximation of the 3-D shape [28,29]. The SfS reconstruction process assumes the reflectance map is known a priori and the albedo map is homogeneous.…”

Section: Terrain Perception Onboard Planetary Roversmentioning

confidence: 99%

“…For terrestrial applications homogeneity of albedos may not always be the case due to non-linearity in natural scenes. However, surfaces on the Moon and Mars tend to have a restricted range of albedos with distinct variations that can be easily detected [28,29]. Furthermore, since the technique relies on the direction of the light source, for example the sun, this can be easily deduced from the rover’s onboard sun sensor.…”

Section: Terrain Perception Onboard Planetary Roversmentioning

confidence: 99%

“…All of these characteristics make it an ideal method for reconstructing the visual scene environment. In fact, recently this technique has been applied to high resolution images from Chang’E-3 (CE-3) lunar mission for lunar soil physical properties analysis [29] and object detection of planetary surficial rocks for autonomous navigation and mapping [28]. Figure 4 illustrates an example of a digital terrain model (DTM) generated using SfS technique.…”

Section: Terrain Perception Onboard Planetary Roversmentioning

confidence: 99%

See 2 more Smart Citations

Towards Camera-LIDAR Fusion-Based Terrain Modelling for Planetary Surfaces: Review and Analysis

Shaukat

Blacker

Spiteri

et al. 2016

Sensors

Self Cite

View full text Add to dashboard Cite

In recent decades, terrain modelling and reconstruction techniques have increased research interest in precise short and long distance autonomous navigation, localisation and mapping within field robotics. One of the most challenging applications is in relation to autonomous planetary exploration using mobile robots. Rovers deployed to explore extraterrestrial surfaces are required to perceive and model the environment with little or no intervention from the ground station. Up to date, stereopsis represents the state-of-the art method and can achieve short-distance planetary surface modelling. However, future space missions will require scene reconstruction at greater distance, fidelity and feature complexity, potentially using other sensors like Light Detection And Ranging (LIDAR). LIDAR has been extensively exploited for target detection, identification, and depth estimation in terrestrial robotics, but is still under development to become a viable technology for space robotics. This paper will first review current methods for scene reconstruction and terrain modelling using cameras in planetary robotics and LIDARs in terrestrial robotics; then we will propose camera-LIDAR fusion as a feasible technique to overcome the limitations of either of these individual sensors for planetary exploration. A comprehensive analysis will be presented to demonstrate the advantages of camera-LIDAR fusion in terms of range, fidelity, accuracy and computation.

show abstract

Section: Terrain Perception Onboard Planetary Roversmentioning

confidence: 99%

Section: Terrain Perception Onboard Planetary Roversmentioning

confidence: 99%

Section: Terrain Perception Onboard Planetary Roversmentioning

confidence: 99%

See 1 more Smart Citation

Towards Camera-LIDAR Fusion-Based Terrain Modelling for Planetary Surfaces: Review and Analysis

Shaukat

Blacker

Spiteri

et al. 2016

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the deepening of people's exploration of outer space, planetary rovers have become the hotspot of planetary exploration research such as visual obstacles, avoiding wheel slip and rough terrain travel, which pose new challenges to the navigation and control of mobile robots (Bouguelia et al, 2017;Spiteri et al, 2016;Wang et al, 2019). Planetary rovers face complex and changing environments in planetary exploration, requiring their drive control systems to have fast dynamic response performance and the advantages of real-time adjustment of controller parameters.…”

Section: Introductionmentioning

confidence: 99%

The adaptive sliding mode control using improved genetic algorithm tuning PID controller for the planetary rover

Yuan

Guo

et al. 2021

AEAT

View full text Add to dashboard Cite

Purpose The purpose of this paper is to resolve the problem of the dynamic response performance of the driving control system for a six-wheeled planetary rover. An adaptive sliding mode controller based on an improved genetic algorithm (IGA) to tune PID sliding surface parameters was used in the driving control system of the planetary rover. Design/methodology/approach First, the mathematical model of planetary rover driving control is established. Second, according to sliding mode variable structure control, an equivalent controller and a disturbance controller are constructed to solve the problem of a multi-disturbance nonlinear driving control system of planetary rovers and an IGA is used to tune PID parameters. Findings Simulation results show that the proposed control algorithm improves the accuracy of the driving control system and optimizes the smoothness of rover motion control. Practical implications The controller based on the IGA to tune PID sliding surface parameters has good self-adaptability and real-time controllability for the control object which is difficult to present a precise mathematical model. Originality/value The advanced control method is adopted to solve the uncertainty and external interference of planetary rovers in a complex environment. The mathematical model of the six-wheeled rover is established as the control object and the uncertainty and external disturbance of the model are considered. The controller based on IGA has good adaptability and real-time performance and the control algorithm can be used to drive robots in complex environments.

show abstract

“…In [28] a deep convolutional network was used for spatio-temporal cue analysis for object avoidance in traffic conditions, by saliency-based modeling of the importance of scene objects. [33] presents a salient object detection method on monocular imagery for planetary rover robots working on images with homogeneous background without the need for a priori training. [15], [16] introduced a monocular obstacle avoidance method for both indoor and outdoor environments, using a depth-like feature map (Dmap) based on relative focus maps, not requiring a priori training or learning of specific environments or objects categories.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Monocular Obstacle Avoidance by Salient Feature Fusion

Manno-Kovacs

Kovács

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

We present a monocular obstacle avoidance method based on a novel image feature map built by fusing robust saliency features, to be used in embedded systems on lightweight autonomous vehicles. The fused salient features are a textural-directional Harris based feature map and a relative focus feature map. We present the generation of the fused salient map, along with its application for obstacle avoidance. Evaluations are performed from a saliency point of view, and for the assessment of the method's applicability for obstacle avoidance in simulated environments. The presented results support the usability of the method in embedded systems on lightweight unmanned vehicles.

show abstract

Structure augmented monocular saliency for planetary rovers

Cited by 3 publications

References 42 publications

Towards Camera-LIDAR Fusion-Based Terrain Modelling for Planetary Surfaces: Review and Analysis

Towards Camera-LIDAR Fusion-Based Terrain Modelling for Planetary Surfaces: Review and Analysis

The adaptive sliding mode control using improved genetic algorithm tuning PID controller for the planetary rover

Lightweight Monocular Obstacle Avoidance by Salient Feature Fusion

Contact Info

Product

Resources

About