Toward a computational approach for collision avoidance with real-world scenes

2003 ◽  
Author(s):  
Matthias S. Keil ◽  
Angel Rodriguez-Vazquez
Keyword(s):  
Collision Avoidance ◽  
Real World ◽  
Computational Approach

Collision Avoidance for a Multiple-DOF Manipulator Based on Empty Space Analysis of the 3-D Real World

1992 ◽  
Vol 4 (5) ◽  
pp. 430-436 ◽  
Author(s):  
Hiromu Onda ◽  
◽  
Tsutomu Hasegawa ◽  
Toshihiro Matsui ◽  
Keyword(s):  
Collision Avoidance ◽  
Real World ◽  
Degrees Of Freedom ◽  
Empty Space ◽  
Joint Space ◽  
Degree Of Freedom ◽  
New Method ◽  
Promising Direction ◽  
Space Analysis ◽  
Path Search

This paper describes a new method for finding collisionfree paths for a multiple-degree of freedom (DOF) manipulator with rotational joints and a grasped object. The method first analyzes the structure of empty space in the 3-D workspace. Based on this space analysis, the path search is divided and direction which appears to be most promising is determined in the 3-D workspace. Finally, the path search is systematically executed in the joint space in the direction equivalent to the promising direction. This method is applicable to various problems regardless of the number of degrees of freedom of the manipulator, its structure, and the presence of a grasped object.

scholarly journals On Comparing and Classifying Several Independent Linear and Non-Linear Regression Models with Symmetric Errors

Symmetry ◽  
2019 ◽  
Vol 11 (6) ◽  
pp. 820 ◽  
Author(s):  
Ji-jun ◽  
Mahmoudi ◽  
Baleanu ◽  
Maleki
Keyword(s):  
Data Mining ◽  
Linear Regression ◽  
Real World ◽  
Regression Models ◽  
Computational Approach ◽  
Parametric Methods ◽  
Linear Regression Models ◽  
Science Data ◽  
Non Linear ◽  
Real World Problems

In many real world problems, science fields such as biology, computer science, data mining, electrical and mechanical engineering, and signal processing, researchers aim to compare and classify several regression models. In this paper, a computational approach, based on the non-parametric methods, is used to investigate the similarities, and to classify several linear and non-linear regression models with symmetric errors. The ability of each given approach is then evaluated using simulated and real world practical datasets.

scholarly journals iADA*-RL: Anytime Graph-Based Path Planning with Deep Reinforcement Learning for an Autonomous UAV

2021 ◽  
Vol 11 (9) ◽  
pp. 3948
Author(s):  
Aye Aye Maw ◽  
Maxim Tyan ◽  
Tuan Anh Nguyen ◽  
Jae-Woo Lee
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Real Time ◽  
Collision Avoidance ◽  
Real World ◽  
Mission Planning ◽  
Planning System ◽  
Local Planning ◽  
Planning Algorithm ◽  
Path Planning Algorithm

Path planning algorithms are of paramount importance in guidance and collision systems to provide trustworthiness and safety for operations of autonomous unmanned aerial vehicles (UAV). Previous works showed different approaches mostly focusing on shortest path discovery without a sufficient consideration on local planning and collision avoidance. In this paper, we propose a hybrid path planning algorithm that uses an anytime graph-based path planning algorithm for global planning and deep reinforcement learning for local planning which applied for a real-time mission planning system of an autonomous UAV. In particular, we aim to achieve a highly autonomous UAV mission planning system that is adaptive to real-world environments consisting of both static and moving obstacles for collision avoidance capabilities. To achieve adaptive behavior for real-world problems, a simulator is required that can imitate real environments for learning. For this reason, the simulator must be sufficiently flexible to allow the UAV to learn about the environment and to adapt to real-world conditions. In our scheme, the UAV first learns about the environment via a simulator, and only then is it applied to the real-world. The proposed system is divided into two main parts: optimal flight path generation and collision avoidance. A hybrid path planning approach is developed by combining a graph-based path planning algorithm with a learning-based algorithm for local planning to allow the UAV to avoid a collision in real time. The global path planning problem is solved in the first stage using a novel anytime incremental search algorithm called improved Anytime Dynamic A* (iADA*). A reinforcement learning method is used to carry out local planning between waypoints, to avoid any obstacles within the environment. The developed hybrid path planning system was investigated and validated in an AirSim environment. A number of different simulations and experiments were performed using AirSim platform in order to demonstrate the effectiveness of the proposed system for an autonomous UAV. This study helps expand the existing research area in designing efficient and safe path planning algorithms for UAVs.

USING A MOBILE ROBOT TO STUDY LOCUST COLLISION AVOIDANCE RESPONSES

1999 ◽  
Vol 09 (05) ◽  
pp. 405-410 ◽  
Author(s):  
MARK BLANCHARD ◽  
PAUL F. M. J. VERSCHURE ◽  
F. CLAIRE RIND
Keyword(s):  
Neural Network ◽  
Mobile Robot ◽  
Collision Avoidance ◽  
Neural Network Model ◽  
Real World ◽  
Biological System ◽  
Neural Circuits ◽  
Movement Detector ◽  
Visual Systems

The visual systems of insects perform complex processing using remarkably compact neural circuits, yet these circuits are often studied using simplified stimuli which fail to reveal their behaviour in more complex visual environments. We address this issue by testing models of these circuits in real-world visual environments using a mobile robot. In this paper we focus on the lobula giant movement detector (LGMD) system of the locust which responds selectively to objects which approach the animal on a collision course and is thought to trigger escape behaviours. We show that a neural network model of the LGMD system shares the preference for approaching objects and detects obstacles over a range of speeds. Our results highlight aspects of the basic response properties of the biological system which have important implications for the behavioural role of the LGMD.

scholarly journals Evaluation of PNT Error Limits Using Real World Close Encounters from AIS Data

2021 ◽  
Vol 9 (2) ◽  
pp. 149
Author(s):  
Evelin Engler ◽  
Paweł Banyś ◽  
Hans-Georg Engler ◽  
Michael Baldauf ◽  
Frank Sill Torres
Keyword(s):  
Collision Avoidance ◽  
Real World ◽  
Simplified Model ◽  
Automatic Identification ◽  
Identification System ◽  
Traffic Data ◽  
Close Encounters ◽  
Data Provision ◽  
Erroneous Data ◽  
Better Than

Collision avoidance is one of the main tasks on board ships to ensure safety at sea. To comply with this requirement, the direct ship environment, which is often modelled as the ship’s domain, has to be kept free of other vessels and objects. This paper addresses the question to which extent inaccuracies in position (P), navigation (N), and timing (T) data impact the reliability of collision avoidance. Employing a simplified model of the ship domain, the determined error bounds are used to derive requirements for ship-side PNT data provision. For this purpose, vessel traffic data obtained in the western Baltic Sea based on the automatic identification system (AIS) is analysed to extract all close encounters between ships considered as real-world traffic situations with a potential risk of collision. This study assumes that in these situations, erroneous data can lead to an incorrect assessment of the situation with regard to existing collision risks. The size of the error determines whether collisions are detected, spatially incorrectly assigned, or not detected. Therefore, the non-recognition of collision risks ultimately determines the limits of tolerable errors in the PNT data. The results indicate that under certain conditions, the probability of non-recognition of existing collision risks can reach non-negligible values, e.g., more than 1%, even though position accuracies are better than 10 m.

scholarly journals Traffic collision avoidance system: false injection viability

2021 ◽  
Author(s):  
John Hannah ◽  
Robert Mills ◽  
Richard Dill ◽  
Douglas Hodson
Keyword(s):  
Collision Avoidance ◽  
Real World ◽  
Situational Awareness ◽  
Simulation Models ◽  
Message Processing ◽  
Closure Rate ◽  
Distributed Computing Systems ◽  
Communication Processes ◽  
Collision Avoidance System ◽  
Traffic Collision

AbstractSafety is a simple concept but an abstract task, specifically with aircraft. One critical safety system, the Traffic Collision Avoidance System II (TCAS), protects against mid-air collisions by predicting the course of other aircraft, determining the possibility of collision, and issuing a resolution advisory for avoidance. Previous research to identify vulnerabilities associated with TCAS’s communication processes discovered that a false injection attack presents the most comprehensive risk to veritable trust in TCAS, allowing for a mid-air collision. This research explores the viability of successfully executing a false injection attack against a target aircraft, triggering a resolution advisory. Monetary constraints precluded access to a physical TCAS unit; instead, this research creates a novel program, TCAS-False Injection Environment (TCAS-FIE), that incorporates real-world distributed computing systems to simulate a ground-based attacker scenario which explores how a false injection attack could target an operational aircraft. TCAS-FIEs’ simulation models are defined by parameters to execute tests that mimic real-world TCAS units during Mode S message processing. TCAS-FIE simulations execute tests over applicable ranges (5–30 miles), altitudes (25–45K ft), and bearings standard for real-world TCAS tracking. The comprehensive tests compare altitude, measure range closure rate, and measure signal strength from another aircraft to determine the delta in bearings over time. In the attack scenario, the ground-based adversary falsely injects a spoofed aircraft with characteristics matching a Boeing 737-800 aircraft, targeting an operational Boeing 737-800 aircraft. TCAS-FIE completes 555,000 simulations using the various ranges, altitudes, and bearings. The simulated success rate to trigger a resolution advisory is 32.63%, representing 181,099 successful resolution advisory triggers out of 555,000 total simulations. The results from additional analysis determine the required ranges, altitudes, and bearing parameters to trigger future resolution advisories, yielding a predictive threat map for aircraft false injection attacks. The resulting map provides situational awareness to pilots in the event of a real-world TCAS anomaly.

Sign in / Sign up

Export Citation Format

Share Document