Given the COVID-19 pandemic and associated restrictions, as the safety of people is of the highest priority, we are offering the option for either physical presence or virtual participation in the 2020 International Conference on Computer, Information and Telecommunication Systems (CITS 2020) to be held in Hangzhou, China in the period 5-7 October, 2020.
ECCV 2020 – Call for Participants: 3rd ACRV Probabilistic Object Detection (PrOD) Challenge
June 2nd, 2020
Daniela Lopez de Luise 3rd Probabilistic Object Detection (PrOD) Challenge (ECCV)
The Australian Centre for Robotic Vision is pleased be running the third iteration of their first robotic vision challenge on probabilistic object detection. In the probabilistic object detection (PrOD) challenge, participants have to detect objects in video data and provide accurate estimates of spatial and semantic uncertainty. High performing competitors in this iteration of the challenge will be invited to present their work online at our ECCV 2020 Workshop Beyond mAP: Reasessing the Evaluation of Object Detectors and receive a monetary prize.
To compete in the challenge and for the full challenge details, please see our competition website (https://competitions.codalab.org/competitions/20597)
Important Dates
=============
- Final Detection Submissions Due – 14th July 2020 Midnight UTC
- Final Paper Submissions Due – 21st July 2020 Midnight UTC
- Winner Announcements and Workshop Invitations Sent – 28th July 2020
- ECCV Workshop (online) – 28th August 2020
Overview
========
To aid in developing computer vision systems that can be easily applied to a robotics domain, our challenge encourages development of probabilistic object detection systems that provide meaningful estimates of both spatial and semantic uncertainty. This enable object detection to be utilised like any other sensor within already trusted Bayesian fusion frameworks
In contrast to traditional object detection challenges (such as COCO), our challenge evaluates detections using the new probability-based detection quality (PDQ) measure which rewards accurate uncertainty estimates, and penalises both overconfident and underconfident detections.
Within the challenge, competitors will detect 30 classes of object in over 56,000 images from 18 high-fidelity simulated video sequences spanning 3 unique environments viewed at 3 different simulated robot heights with both day and night lighting conditions.
As well as the ECCV 2020 PrOD challenge, we have a continuous evaluation server available for those who want to develop work in this field of research.
We invite anyone who is interested in object detection and appreciates a good challenge to please participate and compete in the competition so that we may continue to push the state-of-the-art in object detection in directions more suited to robotics applications.
ECCV 2020 PrOD Competition: https://competitions.codalab.org/competitions/20597
Continuous PrOD Challenge: https://competitions.codalab.org/competitions/20595
Contact Details
============
E-mail: contact@roboticvisionchallenge.org
Twitter: @RobVisChallenge
Website: roboticvisionchallenge.org
CfP RSS Workshop on Perception and Control for Fast and Agile Super-Vehicles
June 2nd, 2020
Daniela Lopez de Luise “Perception and Control for Fast and Agile Super-Vehicles” to be held on
the 12th of July as a fully virtual event.
We invite 2-page extended abstract submissions for original work in
perception and control for high speed navigation and topics of interest
to this workshop. Topics of interest to this workshop are (but not
limited to):
• Autonomous drone racing
• High speed localization and mapping
• Perception aware control and planning
• Trajectory optimization for aggressive flight
• Robust control for high speed flight
• Accurate simulation of highly agile and fast aerial vehicles
Authors will have the opportunity to participate in a short invited
talk at the workshop.
** Important dates:
Abstract submission deadline: June 14th 2020
Acceptance Notification: June 21st 2020
Workshop date: July 12th 2020
Please email all submissions to super-vehicles-rss20-submit@mit.edu with
‘RSS20 Super Vehicles’ in the subject line.
** Abstract for the workshop
As autonomous aerial vehicles not only become more robust and capable,
but also are slowly being adopted in many industrial tasks, a novel
branch of autonomy has recently caught the interest of many researchers:
autonomous drone racing. Not only does it combine the difficulties in
perception, estimation, planning, control, and their intersections, but
it also tests their ability to perform under harsh, real-world conditions.
Expert human pilots have demonstrated an astonishing level of control,
racing remotely controlled drones at their physical limits, and
inspiring roboticists to push the algorithmic limits to a
human-competitive level. As advances in algorithmic perception and
control for fast and agile robotic vehicles materialize, autonomous
racing vehicles are quickly approaching the ability to contend against
human pilots in head to head races. Most recently, Lockheed Martin,
NVIDIA and the Drone Racing League (DRL) successfully organized the
first season of the AlphaPilot program
(https://www.herox.com/alphapilot) and the AIRR drone racing challenge
(https://thedroneracingleague.com/airr/), where multiple teams have
successfully deployed and raced their autonomy algorithms against each
other. These advances may ultimately lead to autonomous super-vehicles,
i.e., next-generation autonomous robots that are capable of achieving
super-human maneuvering and racing capabilities. The resulting
algorithms may become invaluable components of high-throughput autonomy
software, e.g., to maneuver cars out of traffic accidents. However, the
development of these super-vehicles brings significant challenges. While
perceiving the environment at high speeds with low latency has been
investigated throughout the last decade, many open research questions
still remain. On the other side, time-optimal planning with well known
or learned dynamic and aerodynamic models could give autonomous drones
an advantage over human pilots, or let them learn from each other. The
purpose of this workshop is to identify gaps in current techniques, and
discuss possible solutions to the remaining and newly uncovered research
questions.. Is end to end deep learning a viable option to solve these
high speed interactions? What can we model, what can we learn, and could
we combine these techniques to achieve superhuman capabilities? What are
the transfer gaps between simulation, learning and real world systems,
and how can we bridge them to achieve truly superior autonomous mobile
robots?
Organizers:
Varun Murali, MIT
Phillip Foehn, UZH
Prof. Davide Scaramuzza, UZH
Prof. Sertac Karaman, MIT
Call for Participants – ACRV Robotic Vision Scene Understanding Challenge
June 2nd, 2020
Daniela Lopez de Luise The Australian Centre for Robotic Vision is pleased to announce a new robotic vision challenge on scene understanding. In our challenge, participants will control a robotic agent using simple OpenAI Gym-style controls within a virtual environment to map out the cuboid locations of objects in 3D space. A cash prize of $2,500 USD will be split among high-performing participants in our challenge and they will also receive the opportunity to run their scene understanding algorithms, with no modifications, on a real robotic platform.
Important Dates
- Final submissions to EvalAI Due – 2nd September 2020
- Accompanying Paper submissions – 2nd October 2020
- Result notifications – 16th October 2020
The Robotic Vision Scene Understanding Challenge evaluates how well a robotic vision system can understand the semantic and geometric aspects of its environment. There are two tasks in this challenge: Object-based Semantic Mapping/SLAM, and Scene Change Detection.
Semantic SLAM: Participants use a robot to traverse around the environment, building up an object-based semantic map.
Scene change detection (SCD): Participants use a robot to traverse through two different instances of an environment. Between instances some objects are added or removed and participants must produce an object-based semantic map describing the changes between scenes.
- BenchBot a complete software stack for running semantic scene understanding algorithms
- The BenchBot API allowing simple interfacing with robots, supporting OpenAI Gym-style approaches
- Running algorithms in realistic 3D simulation powered by Nvidia's Isaac simulator, and on real robots, with only a few lines of Python code
- Easy-to-use-scripts for running simulated environments, executing code on a simulated robot, evaluating semantic scene understanding results, and automating code execution across multiple environments
- Opportunities for the best teams to execute their code on a real robot in our lab
More Information:
Challenge server: https://evalai.cloudcv.org/web/challenges/challenge-page/625
BenchBot software stack: http://benchbot.org
Challenge overview video: https://youtu.be/jQPkV29KFv
e-mail: contact@roboticvisionchallenge.org
Website: http://roboticvisionchallenge.org
Slack Workspace: roboticvision-hmc7922.slack.com
Twitter: @robVisChallenge
Social Robotics for Neurodevelopmental Disorders, ICRA 2020
June 2nd, 2020
Daniela Lopez de Luise Workshop on Social Robotics for
Neurodevelopmental Disorders
Paris, France
June 2nd, 2020
In conjunction with
The IEEE International Conference on Robotics and Automation
ICRA 2020
Email: icra2020ndd@easychair.org
Website: https://icra2020ndd.wordpress.com/
******************************************************
In light of the ongoing COVID-19 pandemic, the in-person gathering of ICRA 2020 in Paris has been canceled. ICRA 2020 will be held only as a virtual conference. Therefore, the workshop on “Social Robotics for Neurodevelopmental Disorders” will be held as virtual event the 2nd of June, between 15:00 and 17:30 (CEST), according to the new schedule: https://icra2020ndd.wordpress.com/program/



