An interactive physics-based unmanned ground vehicle simulator leveraging open source gaming technology: progress in the development and application of the virtual autonomous navigation environment (VANE) desktop

Abstract

It is widely recognized that simulation is pivotal to vehicle development, whether manned or unmanned. There are few dedicated choices, however, for those wishing to perform realistic, end-to-end simulations of unmanned ground vehicles (UGVs). The Virtual Autonomous Navigation Environment (VANE), under development by US Army Engineer Research and Development Center (ERDC), provides such capabilities but utilizes a High Performance Computing (HPC) Computational Testbed (CTB) and is not intended for on-line, real-time performance. A product of the VANE HPC research is a real-time desktop simulation application under development by the authors that provides a portal into the HPC environment as well as interaction with wider-scope semi-automated force simulations (e.g. OneSAF). This VANE desktop application, dubbed the Autonomous Navigation Virtual Environment Laboratory (ANVEL), enables analysis and testing of autonomous vehicle dynamics and terrain/obstacle interaction in real-time with the capability to interact within the HPC constructive geo-environmental CTB for high fidelity sensor evaluations. ANVEL leverages rigorous physics-based vehicle and vehicle-terrain interaction models in conjunction with high-quality, multimedia visualization techniques to form an intuitive, accurate engineering tool.The system provides an adaptable and customizable simulation platform that allows developers a controlled, repeatable testbed for advanced simulations. ANVEL leverages several key technologies not common to traditional engineering simulators, including techniques from the commercial video-game industry. These enable ANVEL to run on inexpensive commercial, off-the-shelf (COTS) hardware. In this paper, the authors describe key aspects of ANVEL and its development, as well as several initial applications of the system.

Simulated gold-standard for quantitative evaluation of monocular vision algorithms

“…A recent physics-based example from the literature is the virtual autonomous navigation environment (VANE) and ANVEL platforms. 23 The reader can also refer to the internet for more expensive and custom business solutions, such as Scale AI. While the number of SIM possibilities is endless, these tools are only a part of the big SIM picture.…”

A Method of System Effectiveness Analysis for Remote-Operated Unmanned Ground Vehicles Using OneSAF

“…미국을 비롯한 여러 선진국에서는 각종 모델링 시뮬레이션 기법들을 응용하여 새로운 모델을 개발하고 지속적으로 발전 시키고 있다. 미 육군에서는 공학급 무인차량 시뮬레이션 모 델인 ANVEL(Autonomous Navigation Virtual Environment Labo-ratory)와 교전급 시뮬레이션 프레임워크인 OneSAF(One SemiAutomated Forces)를 연동하여 대규모 전장 환경 하에서의 무 인체계 성능 및 체계효과를 분석하였으며 (Rohde et al, 2009), 미 육군 연구소에서도 모의분석용 무인 화생방 정찰차량의 오 염지역 탐색 알고리즘을 OneSAF를 이용해 분석하여 체계 개 념 설계 시 반영한 바 있다 (Fields et al, 2003). 네트워크 기반 무인체계 원격조종 기능 모의와 관련해서는 네트워크 시뮬레 이터인 OPNET을 무인체계 시뮬레이터에 연동시켜 네트워크 성능 변화에 영향을 주는 주요 매개 변수를 식별하는 민감도 분석연구를 수행한 사례도 있다 (Durham et al, 2009 (Johnson et al, 2010).…”

Multi Agent System Optimization in Virtual Vehicle Testbeds

“…However, previous work on virtual testbeds for autonomous vehicles focussed highly on specialized partial aspects such as real-time simulation with state-of-the-art graphics [20] [18], visualization for mission analysis [7] or sensor data generation for space robotic applications [11]. As the everincreasing demand of sophisticated simulation as well as appealing graphical visualization increases the amount of interacting virtual testbed components, state-of-the-art virtual testbeds introduce centralized simulation data structures which are concurrently shared by all virtual testbed components [20][23] [22][17] [15].…”

“…The domain framework used in our approach should be a centralized solution in order to maintain software engineering advantages from current virtual testbed approaches [18][17] but should not introduce a bottleneck to the overall simulation and multi-agent system optimization. We presented a wait-free concurrency control management approach in [23][24] [22].…”

“…They are frequently used in fields like space robotics [10] [22], underwater vehicles [7], or military ground vehicles [20]. In addition, it is widely recognized that simulation is pivotal to vehicle development, whether manned or unmanned [18]. Virtual testbeds are constituted by a sophisticated physically-based simulation of both the vehicle and its designated environment, as well as real-time, immersive rendering and 3D interaction techniques for the direct feedback and manipulation of the vehicle.…”