CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge

Tranzatto, Marco; Mascarich, Frank; Bernreiter, Lukas; Godinho, Carolina; Camurri, Marco; Khattak, Shehryar; Dang, Tung T.; Reijgwart, Victor; Loeje, Johannes; Wisth, David; Zimmermann, Samuel; Nguyen, Huan X.; Solanka, Lukas; Buchanan, Russell; Bjelonic, Marko; Khedekar, Nikhil; Valceschini, Mathieu; Jenelten, Fabian; Dharmadhikari, Mihir; Homberger, Timon; Petris, Paolo De; Wellhausen, Lorenz; Kulkarni, Mihir; Miki, Tsuneharu; Hirsch, Satchel; Montenegro, Markus; Papachristos, Christos; Tresoldi, Fabian; Carius, Jan; Valsecchi, Giorgio; Meyer, Konrad; Wu, Xiangyu; Nieto, Juan J.; Smith, Andy; Hutter, Marco; Siegwart, Roland; Mueller, Mark W.; Fallon, Maurice; Alexis, Kostas

doi:10.48550/arxiv.2201.07067

Cited by 10 publications

(11 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…framework, CompSLAM [33]. This framework was used by team CERBERUS [14] during their winning run of the DARPA Subterranean challenge, and is capable of handling single estimation failures through multi-modal sensor fusion. For the purpose of this work, the proposed method replaces the LiDAR degeneracy detection module in CompSLAM, which is originally based on the work of [13].…”

Section: B Field Experimentsmentioning

confidence: 99%

Learning-based Localizability Estimation for Robust LiDAR Localization

Nubert

Walther

Khattak

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

LiDAR-based localization and mapping is one of the core components in many modern robotic systems due to the direct integration of range and geometry, allowing for precise motion estimation and generation of high quality maps in real-time. Yet, as a consequence of insufficient environmental constraints present in the scene, this dependence on geometry can result in localization failure, happening in self-symmetric surroundings such as tunnels. This work addresses precisely this issue by proposing a neural network-based estimation approach for detecting (non-)localizability during robot operation. Special attention is given to the localizability of scan-to-scan registration, as it is a crucial component in many LiDAR odometry estimation pipelines. In contrast to previous, mostly traditional detection approaches, the proposed method enables early detection of failure by estimating the localizability on raw sensor measurements without evaluating the underlying registration optimization. Moreover, previous approaches remain limited in their ability to generalize across environments and sensor types, as heuristic-tuning of degeneracy detection thresholds is required. The proposed approach avoids this problem by learning from a collection of different environments, allowing the network to function over various scenarios. Furthermore, the network is trained exclusively on simulated data, avoiding arduous data collection in challenging and degenerate, often hardto-access, environments. The presented method is tested during field experiments conducted across challenging environments and on two different sensor types without any modifications. The observed detection performance is on par with state-ofthe-art methods after environment-specific threshold tuning 1 .

show abstract

Section: B Field Experimentsmentioning

confidence: 99%

Learning-based Localizability Estimation for Robust LiDAR Localization

Nubert

Walther

Khattak

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…This approach has proven to perform well in various real world scenarios, e.g. in [14], however, the performance of the approach relies on heuristically defined eigenvalue thresholds that are highly dependent on the environment and the deployed sensor suite. Similarly, [15] relies on the condition number to determine the health of the optimization process and includes partial constraints along non-degenerate direction for sensor fusion.…”

Section: Related Workmentioning

confidence: 99%

“…While an e-value threshold of at least 110 is required to reliably detect degeneracy, the network detects the degeneracy along the robot's y-axis without any intervention. by team CERBERUS [14] during their winning run of the DARPA Subterranean challenge, and is capable of handling single estimation failures through multi-modal sensor fusion. For the purpose of this work, the proposed method replaces the LiDAR degeneracy detection module in CompSLAM, which is originally based on the work of [13].…”

Section: B Field Experimentsmentioning

confidence: 99%

Learning-based Localizability Estimation for Robust LiDAR Localization

Nubert¹,

Walther²,

Khattak³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

LiDAR-based localization and mapping is one of the core components in many modern robotic systems due to the direct integration of range and geometry, allowing for precise motion estimation and generation of high quality maps in real-time. Yet, as a consequence of insufficient environmental constraints present in the scene, this dependence on geometry can result in localization failure, happening in self-symmetric surroundings such as tunnels. This work addresses precisely this issue by proposing a neural network-based estimation approach for detecting (non-)localizability during robot operation. Special attention is given to the localizability of scan-to-scan registration, as it is a crucial component in many LiDAR odometry estimation pipelines. In contrast to previous, mostly traditional detection approaches, the proposed method enables early detection of failure by estimating the localizability on raw sensor measurements without evaluating the underlying registration optimization. Moreover, previous approaches remain limited in their ability to generalize across environments and sensor types, as heuristic-tuning of degeneracy detection thresholds is required. The proposed approach avoids this problem by learning from a corpus of different environments, allowing the network to function over various scenarios. Furthermore, the network is trained exclusively on simulated data, avoiding arduous data collection in challenging and degenerate, often hardto-access, environments. The presented method is tested during field experiments conducted across challenging environments and on two different sensor types without any modifications. The observed detection performance is on par with state-ofthe-art methods after environment-specific threshold tuning.

show abstract

“…Multicopters are useful for a wide range of applications such as aerial photography [1] inspection [2], search and rescue [3], and transportation [4] thanks to their simple design and high maneuverability. State estimation is necessary for these applications, which often use onboard sensors such as the GPS [5], camera [6], Lidar [7], and inertial measurement unit [8].…”

Section: Introductionmentioning

confidence: 99%

Perception-Aware Receding Horizon Trajectory Planning for Multicopters With Visual-Inertial Odometry

Chen²,

Sreenath

et al. 2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

Visual inertial odometry (VIO) is widely used for the state estimation of multicopters, but it may function poorly in environments with few visual features or in overly aggressive flights. In this work, we propose a perception-aware collision avoidance trajectory planner for multicopters, that may be used with any feature-based VIO algorithm. Our approach is able to fly the vehicle to a goal position at high speed, avoiding obstacles in an unknown stationary environment while achieving good VIO state estimation accuracy. The proposed planner samples a group of minimum jerk trajectories and finds collisionfree trajectories among them, which are then evaluated based on their speed to the goal and perception quality. Both the motion blur of features and their locations are considered for the perception quality. Our novel consideration of the motion blur of features enables automatic adaptation of the trajectory's aggressiveness under environments with different light levels. The best trajectory from the evaluation is tracked by the vehicle and is updated in a receding horizon manner when new images are received from the camera. Only generic assumptions about the VIO are made, so that the planner may be used with various existing systems. The proposed method can run in real time on a small embedded computer on board. We validated the effectiveness of our proposed approach through experiments in both indoor and outdoor environments. Compared to a perception-agnostic planner, the proposed planner kept more features in the camera's view and made the flight less aggressive, making the VIO more accurate. It also reduced VIO failures, which occurred for the perception-agnostic planner but not for the proposed planner. The ability of the proposed planner to fly through dense obstacles was also validated. The experiment video can be found at https://youtu.be/qO3LZIrpwtQ.

show abstract

CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge

Cited by 10 publications

References 66 publications

Learning-based Localizability Estimation for Robust LiDAR Localization

Learning-based Localizability Estimation for Robust LiDAR Localization

Learning-based Localizability Estimation for Robust LiDAR Localization

Perception-Aware Receding Horizon Trajectory Planning for Multicopters With Visual-Inertial Odometry

Contact Info

Product

Resources

About