Mobile Mapping Indoors and Outdoors with Zebedee CSIRORobotics 2026-09-23 | Mobile Mapping Indoors and Outdoors with Zebedee
[CVPR2023] Learning Partial Correlation based Deep Visual Representation for Image Classification Robotics and Autonomous Systems Group CSIRO Data61 2023-06-16 | Rahman, Saimunur, Piotr Koniusz, Lei Wang, Luping Zhou, Peyman Moghadam, and Changming Sun. "Learning partial correlation based deep visual representation for image classification." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6231-6240. 2023.Visual representation based on covariance matrix has demonstrates its efficacy for image classification by characterising the pairwise correlation of different channels in convolutional feature maps. This paper proposes an Iterative method to solve Sparse Inverse Covariance Estimation (iSICE). Our work obtains a partial correlation based deep visual representation and mitigates the small sample problem often encountered by covariance matrix estimation in CNN. Website: csiro-robotics.github.io/iSICEOpen Source Code: github.com/csiro-robotics/iSICEPaper: http://openaccess.thecvf.com/content/CVPR2023/html/Rahman_Learning_Partial_Correlation_Based_Deep_Visual_Representation_for_Image_Classification_CVPR_2023_paper.htmlResearch collaboration between CSIRO's Embodied AI Cluster, University of Wollongong , Australian National University, University of Sydney, QUT (Queensland University of Technology)
Wild-Places: A Large-Scale Dataset for Lidar Place Recognition in Unstructured Natural Environments Robotics and Autonomous Systems Group CSIRO Data61 2023-05-20 | [ICRA 2023] Introducing Wild-Places, a challenging large-scale dataset and benchmark for lidar place recognition in unstructured, natural environments. Wild-Places contains eight lidar sequences collected with a handheld sensor payload over the course of fourteen months, containing a total of 63K undistorted lidar submaps along with accurate 6DoF ground truth. Our dataset contains multiple revisits both within and between sequences, allowing for both intra-sequence (i.e. loop closure detection) and inter-sequence (i.e. re-localisation) place recognition. We also benchmark several state-of-the-art approaches to demonstrate the challenges that this dataset introduces, particularly the case of long-term place recognition due to natural environments changing over time. Pre-print: arxiv.org/abs/2211.12732Benchmark Website: csiro-robotics.github.io/Wild-PlacesDataset: doi.org/10.25919/jm05-g895If you find this paper helpful for your research, please cite our paper using the following reference: Joshua Knights, Kavisha Vidanapathirana, Milad Ramezani, Sridha Sridharan, Clinton Fookes, and Peyman Moghadam, "Wild-Places: A Large-Scale Dataset for Lidar Place Recognition in Unstructured Natural Environments." IEEE International Conference on Robotics and Automation (ICRA) (2023).
Santas new sleigh Robotics and Autonomous Systems Group CSIRO Data61 2022-12-24 | Bingo (aka Santa) found herself a new sleigh! All of us at CSIRO's Data61 Robotics and Autonomous Systems Group wish everyone a Merry Christmas and Happy Holidays!
Legged Robot Race Robotics and Autonomous Systems Group CSIRO Data61 2022-12-24 | What if we race three commercially available quadruped robots for a bit of fun...? Out of the box configuration, 'full sticks forward' on the remotes on flat ground. Hope you enjoy the results ;-)Note: Flat ground is not the terrain these robots have been designed for, so this is not meant to be an evaluation of their actual performance.Robot operators: Tom Molnar on ANYbotics Anymal C, Fletcher Talbot on Boston Dynamics Spot and Ryan Steindl on Ghost Robotics Vision 60.Videography and commentary: Fabio RuetzFind out more about our work: https://research.csiro.au/robotics/
3DSA Promo Video Robotics and Autonomous Systems Group CSIRO Data61 2022-07-12 | 3D Situational Awareness (3DSA) is an innovative technology that uses security cameras to provide both real-time 3D situational awareness and factory flow analytics. It is a scalable and cost effective solution for distribution centres, warehouses and factories that works independently, and in conjunction with other systems like LiDAR, to provide unmatched insights into flow, productivity, efficiency and safety. 3DSA is an invaluable tool for equipping your business for its Industry 4.0 journey.
LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition - [ICRA2022] Robotics and Autonomous Systems Group CSIRO Data61 2022-05-16 | This is the presentation video of ICRA 2022 paper "LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition"Abstract: Retrieval-based place recognition is an efficient and effective solution for re-localization within a pre-built map, or global data association for Simultaneous Localization and Mapping (SLAM). The accuracy of such an approach is heavily dependent on the quality of the extracted scene-level representation. While end-to-end solutions - which learn a global descriptor from input point clouds - have demonstrated promising results, such approaches are limited in their ability to enforce desirable properties at the local feature level. In this paper, we introduce a local consistency loss to guide the network towards learning local features which are consistent across revisits, hence leading to more repeatable global descriptors resulting in an overall improvement in 3D place recognition performance. We formulate our approach in an end-to-end trainable architecture called LoGG3D-Net. Experiments on two large-scale public benchmarks (KITTI and MulRan) show that our method achieves mean F1max scores of 0.939 and 0.968 on KITTI and MulRan respectively, achieving state-of-the-art performance while operating in near real-time. Github: github.com/csiro-robotics/LoGG3D-NetPre-print: arxiv.org/abs/2109.08336 Website: https://research.csiro.au/robotics/Citation: Kavisha Vidanapathirana, Milad Ramezani, Peyman Moghadam, Sridha Sridharan, and Clinton Fookes. "LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition." IEEE International Conference on Robotics and Automation (ICRA), 2022.Other Related Work:github.com/csiro-robotics/locusgithub.com/csiro-robotics/InCloud
DARPA SubT Challenge - Paintcloud flythrough Robotics and Autonomous Systems Group CSIRO Data61 2022-01-27 | Colourised lidar pointcloud of the multi-agent Wildcat SLAM map generated by robots deployed by Team CSIRO Data61 at the DARPA SubT Challenge final event prizerun at the Louisville Mega Cavern on 24 September 2021.
DARPA SubT Challenge - 3D SLAM flythrough Robotics and Autonomous Systems Group CSIRO Data61 2022-01-27 | Multi-agent globally optimised Wildcat SLAM map from the robots deployed by Team CSIRO Data61 during the 60min prize run at the DARPA SubT Challenge final event at the Louisville Megacavern on 24 September 2021.
Team CSIRO Data61s DARPA SubT Challenge technical approach summary Robotics and Autonomous Systems Group CSIRO Data61 2021-12-06 | Summary of the technical approach used by Team CSIRO Data61 in addressing the DARPA SubT Challenge
Good luck CSIRO Data61 SubT Team! Robotics and Autonomous Systems Group CSIRO Data61 2021-12-05 | Spirit video clip cheering on the CSIRO Data61 SubT team. Video creation and editing by Katrina Lo Surdo, CSIRO.
[IROS2021] CatChatter: Acoustic Perception for Mobile Robots Robotics and Autonomous Systems Group CSIRO Data61 2021-10-01 | There are many examples in nature of animals using acoustics to understand and navigate the world around them. Inspired by this, we train an image-to-image translation network to learn the mapping from recorded chirps and echos from an environment to a 360 degree depth map of the environment. This work is focused on expanding on the capabilities of previously published BatVision in a number of ways. We first propose various methods for data augmentation to help the model generalise on less data. We also propose changes to the model architecture to improve performance and training stability. Finally, we investigate the feasibility of 360 degree scene reconstruction by using more microphones and lidar based 3D SLAM data as ground truth for training the model.You can find the full IEEE RA-L paper here: ieeexplore.ieee.org/document/9472944
Bear vs. Door Robotics and Autonomous Systems Group CSIRO Data61 2021-09-24 | Onboard GoPro footage from one of our BIA5 ATR UGVs nicknamed Bear. This is from the DARPA SubTChallenge Final circuit's preliminary round 2 at the Louisville Mega Cavern, KY, USA on 22 September 2021.
Paintcloud: Colourised pointcloud demonstration Robotics and Autonomous Systems Group CSIRO Data61 2021-09-19 | Colourised pointclouds from the DARPA SubT Challenge Cave circuit event in Chillagoe, Far North Queensland, Australia in September 2020. Please see here for more information: https://research.csiro.au/robotics/darpa-subterranean-challenge-cave-circuit-event-concluded/
Probe-before-step walking strategy for multi-legged robots on terrain with risk of collapse Robotics and Autonomous Systems Group CSIRO Data61 2021-07-14 | Multi-legged robots are effective at traversing rough terrain. However, terrains that include collapsible footholds (i.e. regions that can collapse when stepped on) remain a significant challenge, especially since such situations can be extremely difficult to anticipate using only exteroceptive sensing.State-of-the-art methods typically use various stabilisation techniques to regain balance and counter changing footholds. However, these methods are likely to fail if safe footholds are sparse and spread out or if the robot does not respond quickly enough after a foothold collapse.This paper presents a novel method for multi-legged robots to probe and test the terrain for collapses using its legs while walking. The proposed method improves on existing terrain probing approaches, and integrates the probing action into a walking cycle. A follow the-leader strategy with a suitable gait and stance is presented and implemented on a hexapod robot.Eranda Tennakoon, Thierry Peynot, Jonathan Roberts, Navinda Kottege. Probe-before-step walking strategy for multi-legged robots on terrain with risk of collapse. ICRA 2020, Paris, France.For more information please see: https://research.csiro.au/robotics/paper-probe-before-step-walking-strategy-for-multi-legged-robots-on-terrain-with-risk-of-collapse/The ICRA2020 paper can be found here: https://research.csiro.au/robotics/wp-content/uploads/sites/96/2020/03/2020_ICRA___Eranda___Probe_before_step.pdf
RSS 2021 PROMPT: Probabilistic Motion Primitives basedTrajectory Planning Robotics and Autonomous Systems Group CSIRO Data61 2021-07-07 | Paper: Tobias Low, Tirthankar Bandyopadhyay, Jason Williams, Paulo V K Borges, "PROMPT: Probabilistic Motion Primitives based Trajectory Planning" in Robotics: Science and Systems, 2021.
Bruce - Design and Development of a Dynamic Hexapod Robot Robotics and Autonomous Systems Group CSIRO Data61 2021-06-18 | This introduces Bruce, the CSIRO Dynamic Hexapod Robot capable of autonomous, dynamic locomotion over difficult terrain. This robot is built around Apptronik linear series elastic actuators, and went from design to deployment in under a year by using approximately 80\% 3D printed structural (joints and link) parts. The robot has so far demonstrated rough terrain traversal over grass, rocks and rubble at 0.3m/s, and flat-ground speeds up to 0.5m/s. This was achieved with a simple controller, inspired by RHex, with a central pattern generator, task-frame impedance control for individual legs and no foot contact detection. The robot is designed to move at up to 1.0m/s on flat ground with appropriate control, and was deployed into the the DARPA SubT Challenge Tunnel circuit event in August 2019. Full paper: arxiv.org/abs/2011.00523
Autonomous Obstacle Legipulation with a Hexapod Robot Robotics and Autonomous Systems Group CSIRO Data61 2021-06-18 | Legged robots traversing in confined environments could find their only path is blocked by obstacles. In circumstances where the obstacles are movable, a multilegged robot can manipulate the obstacles using its legs to allow it to continue on its path. We present a method for a hexapod robot to autonomously generate manipulation trajectories for detected obstacles. Using a RGB-D sensor as input, the obstacle is extracted from the environment and filtered to provide key contact points for the manipulation algorithm to calculate a trajectory to move the obstacle out of the path. Experiments on a 30 degree of freedom hexapod robot show the effectiveness of the algorithm in manipulating a range of obstacles in a 3D environment using its front legs. Full paper: arxiv.org/abs/2011.06227
Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling (ICRA 2021) Robotics and Autonomous Systems Group CSIRO Data61 2021-05-25 | This video is part of the paper: "Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling" IEEE International Conference on Robotics and Automation (ICRA), 2021. Paper Link: arxiv.org/abs/2011.14497GitHub Code: github.com/csiro-robotics/locusAbstract: Place Recognition enables the estimation of a globally consistent map and trajectory by providing non-local constraints in Simultaneous Localisation and Mapping (SLAM). This paper presents Locus, a novel place recognition method using 3D LiDAR point clouds in large-scale environments. We propose a method for extracting and encoding topological and temporal information related to components in a scene and demonstrate how the inclusion of this auxiliary information in place description leads to more robust and discriminative scene representations. Second-order pooling along with a non-linear transform is used to aggregate these multi-level features to generate a fixed-length global descriptor, which is invariant to the permutation of input features. The proposed method outperforms state-of-the-art methods on the KITTI dataset. Furthermore, Locus is demonstrated to be robust across several challenging situations such as occlusions and viewpoint changes in 3D LiDAR point clouds. The open-source implementation is available at: github.com/csiro-robotics/locus
Virtual surfaces and attitude aware planning and behaviours for negative obstacle navigation Robotics and Autonomous Systems Group CSIRO Data61 2021-04-09 | Full paper can be access here: ieeexplore.ieee.org/document/9376244Arxiv version: arxiv.org/abs/2010.16018For more information about CSIRO Robotics: https://research.csiro.au/robotics/
The VL53L1X Sensor Module - VSM Robotics and Autonomous Systems Group CSIRO Data61 2020-11-12 | This video shows the VSM in action on CSIRO's low cost hexapod robot Zero, both in indoor and outdoor environments, demonstrating autonomous obstacle avoidance.For more information, please visit: https://research.csiro.au/robotics/gizmo/
ACRA 2020 Publicity Video Robotics and Autonomous Systems Group CSIRO Data61 2020-11-12 | We invite you to register to the 2020 Australasian Conference on Robotics and Automation. Registration is free!https://www.araa.asn.au/conference/acra-2020/
DARPA Subt - Cave Circuit event - Beta Course Walk-through Robotics and Autonomous Systems Group CSIRO Data61 2020-11-11 | The Beta course walk-through showing the artifact locations and course features. DARPA #SubtChallengePlease see here for more information: https://research.csiro.au/robotics/darpa-subterranean-challenge-cave-circuit-event-concluded/
Data61 CSIRO - Cave Circuit event - Alpha Course Walk-through Robotics and Autonomous Systems Group CSIRO Data61 2020-11-11 | The Alpha course walk-through showing the artifact locations and course features. DARPA #SubtChallengePlease see here for more information: https://research.csiro.au/robotics/darpa-subterranean-challenge-cave-circuit-event-concluded/
DARPA SubT Challenge Cave Circuit event Robotics and Autonomous Systems Group CSIRO Data61 2020-11-11 | DARPA SubT Challenge Cave Circuit event conducted by the CSIRO Data61 team in Chilagoe, Far North Queensland, Australia.Please see here for more information: https://research.csiro.au/robotics/darpa-subterranean-challenge-cave-circuit-event-concluded/
CSIRO Data61 Robotics/Programming Guest Lecture (T2 2020) for Griffith Engineering Students Robotics and Autonomous Systems Group CSIRO Data61 2020-09-02 | As part of our outreach initiatives, our Engineers Katrina Lo Surdo, Team Leader Les Overs and John Scolaro for our sister group Distributed Sensing Systems gave an online guest lecture to second electrical, electronic, mechatronic and software engineering students for a subject which looks at microprocessors/microcontrollers and C programming.Our continued engagement in outreach activities aim to inspire students about options in the areas of robotics, autonomous, and distributed sensing systems, which all form part of our work as the Cyber-Physical Systems Research Program.
PaintCloud: colourisation of 3D map of CSIROs QCAT site Robotics and Autonomous Systems Group CSIRO Data61 2020-08-26 | A video of PaintCloud and Wildcat SLAM from a ground vehicle at QCAT. For more information check: https://research.csiro.au/robotics/paintcloud-colourising-3d-representations-of-the-world-based-on-lidar-data/
CSIROs Data61 DARPA SubT Challenge Colourised cloud fly through Robotics and Autonomous Systems Group CSIRO Data61 2020-06-23 | CSIRO's Data61 Colourised point cloud captured during the DARPA Subterranean Challenge Urban Event in Washington, USA, February 2020. Points and images captured mid-run using CSIRO's CatPack are fused using PaintCloud software intelligently selecting the best scene representation producing a full-resolution coloured point cloud.This research was developed with funding from the Defense Advanced Research Projects Agency (DARPA). The views, opinions and/or findings expressed are those of the author and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S. Government.
Autonomous Ground Vehicle for Landmine Clearance (long): CSIROs Data61 & Molten Labs - Phases 1-5 Robotics and Autonomous Systems Group CSIRO Data61 2020-06-01 | Read more: https://research.csiro.au/robotics/autonomous-ground-vehicle-for-landmine-clearance-phase-1-completed/
Autonomous Ground Vehicle for Landmine Clearance (short): CSIROs Data61 & Molten Labs Phase 1 Robotics and Autonomous Systems Group CSIRO Data61 2020-06-01 | Read more: https://research.csiro.au/robotics/autonomous-ground-vehicle-for-landmine-clearance-phase-1-completed/
Magneto Demo 2019 Robotics and Autonomous Systems Group CSIRO Data61 2020-05-19 | Magneto is a high degrees-of-freedom autonomous inspection robot that are capable of navigating complex ferrous environments. Their flexibility allows them to access visually occluded pockets, thereby improving inspection coverage and quality over human inspectors. We are working collaboratively with Nexxis to commercialise Magneto.For more information visit: https://research.csiro.au/robotics/paper-magneto-a-versatile-multi-limbed-inspection-robot/
Posable Hubs For Robotic Platforms Robotics and Autonomous Systems Group CSIRO Data61 2020-05-07 | This is the work of Hojnik, one of our PhD students working under the supervision of Professor Jonathan Roberts (QUT) and Mr Paul Flick (CSIRO), aiming to increase the traversability of robotic platforms in rough terrains as well as increase chassis stability, which allows carrying of sensitive payloads.This video shows the functionality of a single wheel, independently of the rest of the system, as well as full pose adjustment using all four wheel to maintain a level chassis on sloped terrain.It further demonstrates the rover’s ability to generate motorless, rotational, motion without the use of a DC power motor. This is done by offsetting the hubs to generate a moment about the wheel’s geometric centre of rotation, and convert gravitational potential energy to rotational energy.In addition, it demonstrates active rover wheelbase adjustment which helps the rover dig itself out of a bog.For more information visit: https://research.csiro.au/robotics/patent-approved-for-posable-hubs-for-robotic-platforms/
NeWheel: customisable robot wheels - Pint of Science Australia 2020 Robotics and Autonomous Systems Group CSIRO Data61 2020-05-07 | This work is being developed by Troy Cordie under the supervision of Dr Tirthankar Bandyopadhyay from CSIRO’s Data61 and QUT Professor Jonathan Roberts. Focused on modular field robotics, the work targets the creation of bespoke robots that make working with robotics simpler – so you don’t need to be an engineer. The smart wheels allow existing platforms and tasks to be reconfigured, without the need to build a robot for a specific task. Read more: https://research.csiro.au/robotics/newheel-self-contained-two-degree-of-freedom-robot-wheels/
3D printing of face shields Robotics and Autonomous Systems Group CSIRO Data61 2020-04-22 | We joined a collaborative effort to increase stocks of PPE supplies across Queensland’s public health system to help the fight against COVID-19.
Posable Hubs For Robotic Platforms Robotics and Autonomous Systems Group CSIRO Data61 2020-02-03 | This work is part of Tim Hojnik's PhD project, a partnership between CSIRO's Data61 Robotics and Autonomous Systems Group and the Queensland University of Technology. Visit: research.csiro.au/robotics to learn more.
Robust Photogeometric Localization Over Time for Map-Centric Loop Closure. IEEE RAL 2019 Robotics and Autonomous Systems Group CSIRO Data61 2020-01-15 | Park, C., Kim, S., Moghadam, P., Guo, J., Sridharan, S., & Fookes, C. (2019). Robust Photogeometric Localization Over Time for Map-Centric Loop Closure. IEEE Robotics and Automation Letters, 4(2), 1768-1775.https://research.csiro.au/robotics/elasticity-meets-continuous-time-slam/Download the full paper: ieeexplore.ieee.org/iel7/7083369/7339444/08626520.pdf
Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach, IEEE RAL 2020 Robotics and Autonomous Systems Group CSIRO Data61 2020-01-14 | "Spatiotemporal Camera-LiDAR Calibration: A Targetless and Structureless Approach" by Chanoh Park, Peyman Moghadam, Soohwan Kim, Clinton Fookes, Sridha Sridharan, accepted for publication in the IEEE Robotics and Automation Letters (RA-L), 2020.https://research.csiro.au/robotics/elasticity-meets-continuous-time-slam/
D61+LIVE SBS News: CSIROs Data61 Robotics and Autonomous Systems robots and DARPA project Robotics and Autonomous Systems Group CSIRO Data61 2019-10-17 | CSIRO's Data61 Robotics and Autonomous Systems robots and DARPA project on Channel9 News during the 2019 D61+ LIVE event at Carriageworks, Sydney.How AI and robotics are making our lives safer and easier.
D61+ LIVE Channel9 News: CSIROs Data61 Robotics and Autonomous Systems robots and DARPA project on Robotics and Autonomous Systems Group CSIRO Data61 2019-10-17 | CSIRO's Data61 Robotics and Autonomous Systems robots and DARPA project on Channel9 News during the 2019 D61+ LIVE event at Carriageworks, Sydney.Hear from David Thodey, CSIRO’s Chairman, being interviewed by Chanel 9 News during D61+ Live in Sydney earlier this month about how CSIRO is combining AI, data and robotics to benefit everyday life.
Our facilities [shorter] - Robotics and Autonomous Systems Group CSIROs Data61 Robotics and Autonomous Systems Group CSIRO Data61 2019-07-30 | We work with a broad range of industries, and are open for collaboration. Want to partner with us or use our research facilities? Contact us to learn more.https://research.csiro.au/robotics/who-we-are/our-facilities/
Our facilities - Robotics and Autonomous Systems Group CSIROs Data61 Robotics and Autonomous Systems Group CSIRO Data61 2019-07-30 | We work with a broad range of industries, and are open for collaboration. Want to partner with us or use our research facilities? Contact us to learn more.https://research.csiro.au/robotics/who-we-are/our-facilities/
CSIROs Data61 Titan & Bruce Hexapod Qualification Robotics and Autonomous Systems Group CSIRO Data61 2019-07-30 | CSIRO's Data61 Titan & Bruce Hexapod robots have qualified to participate in the DARPA Subterranean Challenge Tunnel Event in Pittsburgh, USA in August 2019.This research was developed with funding from the Defense Advanced Research Projects Agency (DARPA). The views, opinions and/or findings expressed are those of the author and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S. Government.
ICRA2019 - Local description for robust place recognition using LiDAR intensity Robotics and Autonomous Systems Group CSIRO Data61 2019-05-16 | ICRA 2019 PaperAuthors: Jiadong Guo, Paulo Borges, Chanoh Park, Abel GawelMore info here: https://research.csiro.au/robotics/paper-local-descriptor-for-robust-place-recognition-using-lidar-intensity/
DARPA SubT Challenge - Snapshot of CSIROs STIX Qualification Submission Robotics and Autonomous Systems Group CSIRO Data61 2019-01-25 | CSIRO's Robotics and Autonomous Systems group is competing in the DARPA SubT Challenge. This video depicts a sample of our submission for the STIX (SubT Integration Exercise) qualification. This shows a tracked platform (one of many modalities to be used in the challenge) with our custom perception payload autonomously navigating across rough ground and through a subterranean environment, whilst autonomously detecting and classifying objects. Learn more about our participation in the DARPA SubT Challenge here: https://research.csiro.au/robotics/we-qualified-darpa-subt-challenge-csiro-december-update/This research was developed with funding from the Defense Advanced Research Projects Agency (DARPA). The views, opinions and/or findings expressed are those of the author and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S. Government.Music:Transportation by Audionautix is licensed under a Creative Commons Attribution license (creativecommons.org/licenses/by/4.0)Artist: http://audionautix.com
CSIRO SubT Hexapod Simulation Development Robotics and Autonomous Systems Group CSIRO Data61 2018-12-18 | CSIRO's Robotics and Autonomous Systems group is competing in the DARPA SubT challenge. This video depicts how the simulation of our new hexapod system has developed over the past few months. It depicts the progress from a simple box with minimal physics to a fully dynamically simulated system running a state-of-the-art dynamic control structure. It is also the first sneak preview at the design of our new hexapod platform.Learn more about our participation in the DARPA SubT Challenge here: https://research.csiro.au/robotics/our-work/darpa-subt-challenge-2018/Music:Big Car Theft by Audionautix is licensed under a CreativeCommons Attribution licence(creativecommons.org/licenses/by/4.0)Artist: http://audionautix.comThis research was developed with funding from the Defense Advanced Research Projects Agency (DARPA). The views, opinions and/or findings expressed are those of the author and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S. Government.
ABOUT US - Robotics and Autonomous Systems Group CSIRO Data 61 Robotics and Autonomous Systems Group CSIRO Data61 2018-09-21 | Robotics and Autonomous Systems Group CSIRO Data 61World leaders in advance research and development of robotics and autonomous systems.- 38 years of history- 80+ robotics experts- 20 world first discoveries- 68 partnerships- growing patent's portfolio...and counting!Contact us today! - research.csiro.au/robotics
PoseMap for Localization in Urban Environments - IROS18 Robotics and Autonomous Systems Group CSIRO Data61 2018-07-22 | This video is related to one of the experiments (in particular, the "Urban Driving") described in the paper:"PoseMap: Lifelong, Multi-Environment 3D LiDAR Localization"Philipp Egger, Paulo Vinicius Koerich Borges, Gavin Catt, Andreas Pfrunder, Renaud DubéConference: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)Details: We mapped a suburban neighbourhood (Indooroopilly) in Brisbane, Australia. In an initial mapping run, a total distance of 6.1 km was driven for the map creation. From the point cloud the PoseMap was extracted with only 10.3 MB in size. The map was then used to localize in this area on multiple occasions at regular speeds of 40-60 km/h. All localization runs were successful with no GPS used. Please check the original paper for all the off-road driving results.
PaintCloud: Colourising Point Clouds using Independent Cameras Robotics and Autonomous Systems Group CSIRO Data61 2018-06-13 | A selection of 3D lidar SLAM point clouds colourised using the method and collection described in "Colourising Point Clouds using Independent Cameras" by Pavel Vechersky, Mark Cox, Paulo Borges, Thomas Lowe, IEEE Robotics and Automation Letters, 2018.
Hovermap UAV lidar mapping payload Robotics and Autonomous Systems Group CSIRO Data61 2018-06-07 | This is an overview of the Hovermap UAV lidar mapping payload developed by the CSIRO Autonomous Systems Lab. Hovermap uses our SLAM mapping algorithms (as used in Zebedee) so does not need GPS/INS integration for mapping. This make it suitable for use indoors, underground or around tall structures where GPS is poor. https://wiki.csiro.au/display/ASL/HoverMap
Multispectral Visualization Robotics and Autonomous Systems Group CSIRO Data61 2018-06-07 | We have designed and developed "Spectra" the world's first 3D multispectral fusion and visualization toolkit developed by HeatWave's team at CSIRO ICT Centre.The 3D multispectral models demonstrated in this video are generated by "HeatWave" a small hand-held 3D thermography device that consists of a light-weight thermal camera, a range sensor and visible-light camera to generate precise, dense and complete 3D model of objects with high accuracy, view independent overlaid temperature and visible information.
ICRA2018 Robotics Tour - ABC National News Robotics and Autonomous Systems Group CSIRO Data61 2018-05-31 | ABC National News covering the CSIRO Data61 Robotics and Autonomous Systems Group's facilities tour for the ICRA2018, Brisbane, Australia. Aired 21 May 2018.
