Opportunities and Challenges with Autonomous Racing (Submission deadline Oct 1, 2022)

In motorsport racing, there is a saying that “If everything seems under control, then you are not going fast enough”. Expert racing drivers have split second reaction times and routinely drive at the limits of control, traction, and agility of the racecar - under high-speed and close-proximity situations. Autonomous racing presents unique opportunities and challenges in designing algorithms and hardware that can operate firmly on the limits of perception, planning, and control. Racing has a long and illustrative history of serving as a proving ground for automotive technology. Similarly, autonomous racing has the potential to serve as the litmus test - but this time - for self-driving software. While a large portion of autonomous vehicle research and development is focused on handling routine driving situations, achieving the safety benefits of autonomous vehicles also requires a focus on driving at the limits of the control of the vehicle.

Demonstrating high-speed autonomous racing is considered as a grand challenge for self-driving cars, and making progress here has the potential to enable breakthroughs in agile and safe autonomy. To succeed at racing, an autonomous vehicle is required to perform both precise steering and throttle maneuvers in a physically-complex, uncertain environment, and by executing a series of high-frequency decisions. This makes racing an interesting opportunity to explore the physical and algorithmic limits of autonomous vehicles. Autonomous racing competitions, such as Formula Student Driverless, F1/10 autonomous racing, Roborace, and Indy Autonomous Challenge are, both figuratively and literally, getting a lot of traction and becoming proving grounds for testing perception, planning, and control algorithms at high speeds.

The main objective of this special issue is to solicit high-quality submissions from the robotics community on research challenges specific to high-speed autonomous racing in the field.

The topics on autonomous racing include, but are not limited to:

•Head-to-head multi-agent racing

•Modeling vehicle dynamics at high-speeds

•Overtaking strategies

•State-estimation of opponents

•Racing simulation at scale

•Limits of perception, localization, and planning at high-speeds

•Racing behavior: Adversarial vs Cooperative

•Balancing safe vs aggressive driving policies

•Hardware-software co-design for autonomous racing

•Hardware AI accelerators for perception

•Software stack and architectures for racing

Guest Editorial Team

•Dr. Johannes Betz, University of Pennsylvania [joebetz@seas.upenn.edu]

•Dr. Madhur Behl, University of Virginia [madhur.behl@virginia.edu]

•Dr. Rahul Mangharam, University of Pennsylvania [rahulm@seas.upenn.edu]

•Dr. Venkat Krovi, Clemson University [vkrovi@clemson.edu]

__________________________________________________________________________________

DARPA Subterranean Challenge, Advancement and Lessons Learned from the Finals (Submission closed)

The DARPA Subterranean Challenge (2018-2021), or SubT Challenge for short, was a competition organized by the Defense Advanced Research Projects Agency and facilitated the development of technologies for autonomous exploration and search of challenging underground environments. Through a sequence of grueling competition events, called “Circuits” and the “Final Event”, DARPA challenged teams across the world to develop robotic systems and autonomy solutions capable of undertaking the diverse challenges of tunnel-like settings such as underground mines (“Tunnel Circuit”), urban underground facilities (“Urban Circuit”), and natural cave networks (“Cave Circuit”). The SubT Challenge culminated with an exciting Final Event and a Prize Run which took place in the Louisville Mega Caverns, KY, and involved an environment that combined the diverse challenges of all the circuit environment types. With the competition course being completely unknown and presenting complex challenges related to GPS-denied and sensor-degraded settings, austere navigation conditions, rough and dynamic terrain, multi-level structures, and degraded communications, the teams were evaluated with respect to their ability to detect objects of interest (“artifacts”) and report their location with an absolute error less than 5 m.

This Special Issue of Field Robotics will showcase the contributions pushing the state of the art and will allow reflecting on the lessons learned by the teams that competed in the SubT Challenge Finals. In turn, this will be an opportunity for the wider robotics community to benefit from the work done by the teams and synthesize novel research directions to reach new frontiers on robotics and resilient autonomy. We solicit original contributions that highlight the following aspects in the context of competing in the DARPA SubT Challenge systems track finals:

●Mechanism design

●Systems and control

●Motion and path planning

●Perception

●SLAM

●Multi-agent navigation

●Mission planning

●Data-driven methods

Simultaneously, we welcome dataset contributions and open-source code releases of methods tested and fielded in the challenge finals.

Guest editorial team

1. •Kostas Alexis (NTNU, Team CERBERUS)
   

2. •Navinda Kottege (CSIRO, Team CSIRO-DATA61)
   

3. •Sean Humbert (CU Boulder, Team MARBLE)
   

4. •Sebastian Scherer (CMU, Team Explorer)
   

5. •Ali Agha (JPL, Team CoStar)
   

6. •Jan Faigl (CTU, Team CTU-CRAS-NORLAB)
   

Please contact konstantinos.alexis@ntnu.no for more details

__________________________________________________________________________________

Dynamic Large-Scale Swarm Systems in Urban Environments: Results from the DARPA OFFSET Program (Submission closed)

Individual semi-autonomous unmanned systems have already proven to be useful in a variety of use cases including movie production, agriculture, civil engineering, military operations and insurance. Likewise, small groups of unmanned systems have shown promise, particularly when coordinating to achieve a common goal. Less studied are the potential benefits of large swarms comprising hundreds of inexpensive but capable unmanned systems, largely due to the difficulties associated with creating, or even simulating, such a system. Unmanned system swarms are characterized by large numbers of platforms dynamically cooperating and rapidly adapting to changes in objectives and/or the environment. Unmanned system swarms face many complex research challenges and field-testing these swarms can be a massive undertaking. 

Since it began in 2017, DARPA’s OFFensive Swarm-Enabled Tactics (OFFSET) program has envisioned future small-unit forces using swarms comprising hundreds of unmanned aerial systems (UASs) and unmanned ground systems (UGSs) collaborating to accomplish diverse missions in complex urban environments. By leveraging and combining emerging technologies in swarm autonomy and human-swarm teaming, the OFFSET program has enabled rapid development and practical field-testing of a number of emerging breakthrough capabilities in areas such as:

1. •Swarm Sensing and Perception
   

2. •Swarm System Hardware and Logistics
   

3. •Distributed Planning and Navigation
   

4. •Human-Swarm Interfaces
   

5. •Swarm Simulation at Scale
   

6. •Swarm Tactics and Tactic Development
   

7. •Swarm Communications
   

8. •Swarm System Testing and Evaluation
   

These evolving and integrated capabilities undergo regular and extensive field evaluation with increasing numbers of platforms and complexity of environments to assess current approaches under realistic field conditions. This special issue is intended to highlight the large-scale unmanned system swarm technologies developed and lessons learned in the DARPA OFFSET program, including research articles, field experiments, and hardware/software system descriptions. Researchers and evaluators who participated in the OFFSET program or utilized the technology developed by the program are encouraged to submit original papers that meet Field Robotics guidelines. We seek contributions from participating individuals and organizations describing their role and experimental results including technology providers, integrators, sprinters, evaluators and program management. The topics should address one of the research areas mentioned above or an integrated combination representing the state of the art capabilities achieved under OFFSET.

Guest editorial team:

1. •Dr. Erin Cherry, Northrup Grumman Mission Systems
   

2. •Dr. Timothy Chung, DARPA Tactical Technology Office
   

3. •Dr. Shane Clark, STR
   

4. •Mr. Kyle Usbeck, Systems and Technology Research Corporation
   

__________________________________________________________________________________

Unmanned Marine Systems (submission closed)

This special issue focuses on state-of-the-art developments in maritime robotic systems including autonomy, control, sensing and analysis related to Autonomous Surface Vehicles (ASVs), Autonomous Underwater Vehicles (AUVs) and Unmanned Aerial Systems (UAS). The marine environment is extremely challenging due to the rapid attenuation of the electromagnetic spectrum and the constraints that imposes on underwater communications, sensing and navigation. Marine roboticists, thus, cannot typically rely on systems developed for land based applications but have instead focused on solutions specific to the underwater environment to address critical needs in Marine Archeology, Marine Geology and Geophysics, Fisheries, Polar Studies, Coral Reef Ecology and in the Offshore and Naval domains.

This special issue seeks to obtain a technological snapshot of the current state of research as it bears on these important issues.

As part of the stated goal of the Field Robotics journal, the special issue seeks papers on systems and algorithms that have been tested in the field as opposed to simulations.

The list of topics includes but is not limited to

1. •Vehicle Design
   

2. •Vehicle Navigation
   

3. •Sensor design and data fusion for optical, acoustic, environmental and other sensors suites.
   

4. •Autonomy for individual, multiple and heterogeneous vehicle systems
   

5. •Marine image understanding and information extraction
   

6. •Higher-level autonomy for mission planning and control
   

7. •Biologically inspired approaches to intelligent autonomy for autonomous maritime vehicles
   

8. •The applications of these systems in shallow water, the mid-water column, the deep ocean and polar environments
   

Authors are encouraged to submit multimedia attachments to the paper (data sets, models and videos) as a means of enhancing the submission.

Guest editorial team

Hanumant Singh, Northeastern University (ha.singh@northeastern.edu)

Stefan Williams, University of Sydney (stefan.williams@sydney.edu.au)

Blair Thornton, University of Southampton (B.Thornton@soton.ac.uk)

For comments, suggestions, or requests, please email any of the guest editors.

__________________________________________________________________________________

Advancements and lessons learned during Phase I & II of the DARPA Subterranean Challenge (submission closed)

The DARPA SubT Challenge (2018-2021) is aimed at deploying autonomous robot teams to explore GPS-denied underground environments with degraded wireless communications to search and report locations of predefined artifacts. This is structured as circuit events with the following:

Tunnel circuit: Man-made tunnels such as mining tunnels.
Urban circuit: Underground urban environments such as subways, sewers and industrial buildings.
Cave circuit: Natural caves

Successful deployment in these events requires research and development in rapid mapping, effective navigation, and robust systems, among many other aspects in field robotics. The tunnel circuit was held in August 2019 at the NIOSH Experimental Coal Mines in Pittsburgh, PA, and the urban circuit was held in February 2020 at the Satsop Nuclear Plant in Elma, WA.

This special issue in the Field Robotics will showcase the contributions to the state of the art in field robotics and lessons learned by the teams that competed in the concluded circuit events. This will be an opportunity for the wider robotics community to benefit from work done by the teams to push forward what is possible with autonomous field robots. We solicit original contributions that highlight the following aspects in the context of competing in the DARPA SubT Challenge systems track:

•Mechanism design

•Systems and control

•Motion planning

•Perception

•SLAM

•Multi-agent navigation

•Mission planning

Guest editorial team

Navinda Kottege (CSIRO, Team CSIRO-DATA61)

Ali Agha (JPL, Team CoStar)

Sebastian Scherer (CMU, Team Explorer)

Jan Faigl (CTU, Team CTU-CRAS-NORLAB)

Please contact navinda.kottege@csiro.au for more details.

__________________________________________________________________________________

Robotics Collaborative Technology Alliance (RCTA)-- Developing Autonomous Robotic Team Members for Unstructured Environments ((submission closed)

The impressive growth of investment in driverless cars, warehouse automation, human service robots, and Artificial Intelligence applications in our daily lives is inspiring. However, the majority of this effort assumes a structured environment, which leaves significant unsolved problems for autonomous robots operating in unstructured environments. Beginning in 2010, the U.S. Army Research Laboratory (ARL) funded a ten-year robotics research program called the Robotics Collaborative Technology Alliance (RCTA), which brought together Government, Academic, and Industry robotics scientists and engineers to develop autonomous mobile robot technologies for unstructured environments. While the underlying motivation came from helping soldiers operating in unstructured environments, the benefits extend to scenarios ranging from disasters, to interplanetary exploration, to reducing reliance on extensive prior knowledge in structured environments. In 2016 the objectives of this program were refocused on a system-oriented approach that brought these four research areas together into a set of demonstrable capabilities in application scenarios.

This special issue is intended to highlight robotics technology developed in the RCTA program, including research articles, field experiments, and hardware/software system descriptions. Researchers who participated in the RCTA program over the 2010-2020 period are encouraged to submit papers that meet Field Robotics guidelines. The topics should address one of the research areas mentioned above or a combination representing field robotics capability.

Guest editorial team

Larry Matthies, Jet Propulsion Laboratory/CalTech

Cynthia Matuszek, University of Maryland, Baltimore County

Aaron Johnson, Carnegie Mellon University

Monroe Kennedy III, Stanford University

Please contact dpatel1@loyola.edu for more details.

__________________________________________________________________________________

Special Issue on MBZIRC 2020: Challenges in Autonomous Field Robotics (submission closed)

Robotics has the potential to have an impact that is as transformative as the Internet, with robotics technology poised to fuel a broad range of next-generation products and applications in a diverse array of fields. These include robot applications in disaster response, manufacturing, construction, healthcare and household chores. In the past few decades robotic competitions have been a catalyst for accelerating technological advancements in robotics and autonomous systems. The Mohamed Bin Zayed International Robotics Challenge (MBZIRC) is a biennial robotics competition motivated by the technological challenges facing the next generation of robotics. The enabling technologies for next generation robotic applications include robots working more autonomously in dynamic, unstructured environments, while collaborating and interacting with other robots and humans. MBZIRC 2020 focused on some of these enabling technologies, by providing a demanding set of benchmark robotics challenges, and has attracted some of the best international teams. Similar to other major competitions, MBZIRC provided an environment to foster innovation and technical excellence, while encouraging entertaining performance. 

We encourage authors to submit original work developed to solve the MBZIRC 2020 Challenges. Topics of interest include robotics in unstructured, dynamic outdoor environments, sensing and perception, machine learning, mechanical design, computer architectures, communication, planning, learning, and control.

Guest editorial team

Jorge Dias,  Khailfa University

Paolo Dario, Scuola Superiore Sant’Anna

Lakhmal Seneviratne, Khalifa University

Oussama Khatib, Stanford UNiversity

Satoshi Tadokoro, Tohoku University

Pedro Lima, University of Lisbon