Dynamic Obstacle Avoidance Using Bayesian Occupancy Filter and Approximate Inference

Llamazares, Ángel; Ivan, Vladimir; Molinos, Eduardo J.; Ocaña, Manuel; Vijayakumar, Sethu

doi:10.3390/s130302929

Cited by 19 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The local mapping stage is based on a dynamic occupancy grid called DOMap (Dynamic Occupancy Mapping) [4]. Each cell of this grid stores the probability of occupancy and the estimation of its velocities (v x , v y ).…”

Section: Proposed Methodsmentioning

confidence: 99%

“…While global planning processes determine what is the better way to approach the target, local planning is in charge of avoiding obstacles and keep the robot-human integrity. For this planning is important to use maps, which can be generated in manual or semi-autonomus way, and they can include occupancy or occupancy and velocity information [4].…”

Section: Introductionmentioning

confidence: 99%

“…In this work, we propose an extension of a well known reactive method called Curvature Velocity Method (CVM) to include the information provided by our previous developed DOMap [4]. We test the proposal both in simulated and real scenarios to achieve a robust and safety autonomous navigation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic obstacle avoidance based on curvature arcs

Molinos

Llamazares

Ocaña

et al. 2014

2014 IEEE/SICE International Symposium on System Integration

Self Cite

View full text Add to dashboard Cite

Traditionally, obstacle avoidance algorithms have been developed and applied successfully to mobile robots that work in controlled and static environments. But, when working in real scenarios the problem becomes complex since the scenario is dynamic and the algorithms must be enhanced in order to deal with moving objects. In this paper we propose a new method based on the well known Curvature Velocity Method (CVM) and a probabilistic 3D occupancy and velocity grid, developed by the authors, that can deal with these dynamic scenarios. The proposal is validated in real and simulated environments.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic obstacle avoidance based on curvature arcs

Molinos

Llamazares

Ocaña

et al. 2014

2014 IEEE/SICE International Symposium on System Integration

Self Cite

View full text Add to dashboard Cite

show abstract

“…The goal of [14] is to solve the problem of dynamic obstacle avoidance for a mobile platform by using the stochastic optimal control in terms of safety and energy efficiency framework to compute paths. Authors propose a 3D extension of the Bayesian Occupancy Filter (BOF) to deal with the noise in the sensor data.…”

Section: Papers In the Special Issuementioning

confidence: 99%

Introduction to the Special Issue on “New Trends towards Automatic Vehicle Control and Perception Systems”

Milanés

Bergasa

2013

Sensors

View full text Add to dashboard Cite

Intelligent and automatic systems are making our daily life easier. They are able to automate tasks that, up to now, were performed by humans, freeing them from these tedious tasks. They are mainly based on the classical robotic architectures where the stages of perception-using different sensor sources or even a fusion of a set of them-and planning-where intelligent control systems are applied-play a key role. Among all of the fields in which intelligent systems can be applied, transport systems are considered one of the most promising ones since over one million fatalities-including drivers, pedestrians, cyclists and motorcyclists-are registered each year worldwide and they can definitively help to reduce these figures.The growth in the number of drivers in the last decades, and consequently in the number of vehicles, has made traffic accidents become a major concern in the road transportation sector. Solutions such as building new transport infrastructures-specifically in urban areas where space limitations make it almost impossible-or increasing fines for inappropriate driving have not achieved the goal of reducing the number of fatalities, either in urban environments or highways. New policies on the part of the Governments are focused on the development of a safer, more reliable and more efficient transportation supported by intelligent systems.The field of research in which all these topics fall into is well-known as intelligent transportation systems (ITS). ITS focuses on improving road safety by acting on two possible aspects: on the one hand, the infrastructure and the possibilities of optimizing traffic flow, and on the other hand, acting on the cars with the development of Advanced Driver Assistance Systems (ADAS) and the possibilities of optimizing traffic safety. The final goal is trying to reduce the number of collisions, or at least to mitigate their consequences. In this connection, one of the currently hot topics in the road OPEN ACCESS

show abstract

“…Based on these characteristics and in order to deal with different participants as dynamic obstacles without needed to use several models for each of them, we proposed a probabilistic model of the environment in a previous work [ 23 ], using a Grid-Based DATMO with BOF filter approach. This system was called Dynamic Obstacle Map (DOMap).…”

Section: Introductionmentioning

confidence: 99%

Improved Dynamic Obstacle Mapping (iDOMap)

Llamazares

Molinos

Ocaña

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

The goal of this paper is to improve our previous Dynamic Obstacle Mapping (DOMap) system by means of improving the perception stage. The new system must deal with robots and people as dynamic obstacles using LIght Detection And Range (LIDAR) sensor in order to collect the surrounding information. Although robot movement can be easily tracked by an Extended Kalman Filter (EKF), people’s movement is more unpredictable and it might not be correctly linearized by an EKF. Therefore, to deal with a better estimation of both types of dynamic objects in the local map it is recommended to improve our previous work. The DOMap has been extended in three key points: first the LIDAR reflectivity remission is used to make more robust the matching in the optical flow of the detection stage, secondly static and a dynamic occlusion detectors have been proposed, and finally a tracking stage based on Particle Filter (PF) has been used to deal with robots and people as dynamic obstacles. Therefore, our new improved-DOMap (iDOMap) provides maps with information about occupancy and velocities of the surrounding dynamic obstacles (robots, people, etc.) in a more robust way and they are available to improve the following planning stage.

show abstract

Dynamic Obstacle Avoidance Using Bayesian Occupancy Filter and Approximate Inference

Cited by 19 publications

References 28 publications

Dynamic obstacle avoidance based on curvature arcs

Dynamic obstacle avoidance based on curvature arcs

Introduction to the Special Issue on “New Trends towards Automatic Vehicle Control and Perception Systems”

Improved Dynamic Obstacle Mapping (iDOMap)

Contact Info

Product

Resources

About