Publications
Self-Supervised Learning of Visual Robot Localization Using LED State Prediction as a Pretext Task
Mirko Nava, Nicholas Carlotti, Luca Crupi, Daniele Palossi, and Alessandro Giusti
in IEEE Robotics and Automation Letters, vol. TBD, pp. TBD, 2024.
@article{nava2024self,
author={Nava, Mirko and Carlotti, Nicholas and Crupi, Luca and Palossi, Daniele and Giusti, Alessandro},
journal={IEEE Robotics and Automation Letters},
title={Self-Supervised Learning of Visual Robot Localization Using LED State Prediction as a Pretext Task},
year={2024},
volume={9},
number={4},
pages={3363-3370},
doi={10.1109/LRA.2024.3365973},
}
Abstract
We propose a novel self-supervised approach for learning to localize robots equipped with controllable LEDs visually. We rely on a few training samples labeled with position ground truth and many training samples in which only the LED state is known, whose collection is cheap. We show that using LED state prediction as a pretext task significantly helps to solve the visual localization end task. The resulting model does not require knowledge of LED states during inference. We instantiate the approach to visual relative localization of nano-quadrotors: experimental results show that using our pretext task significantly improves localization accuracy (from 68.3% to 76.2%) and outperforms alternative strategies, such as a supervised baseline, model pre-training, or an autoencoding pretext task. We deploy our model aboard a 27-g Crazyflie nano-drone, running at 21 fps, in a position-tracking task of a peer nano-drone. Our approach, relying on position labels for only 300 images, yields a mean tracking error of 4.2 cm versus 11.9 cm of a supervised baseline model trained without our pretext task.
Self-Supervised Prediction of the Intention to Interact With a Service Robot
Gabriele Abbate, Alessandro Giusti, Viktor Schmuck, Oya Celiktutan, and Antonio Paolillo
in Robotics and Autonomous Systems, 2023.
Bibtex entry here.
Abstract
A service robot can provide a smoother interaction experience if it has the ability to proactively detect whether a nearby user intends to interact, in order to adapt its behavior e.g. by explicitly showing that it is available to provide a service. In this work, we propose a learning-based approach to predict the probability that a human user will interact with a robot before the interaction actually begins; the approach is self-supervised because after each encounter with a human, the robot can automatically label it depending on whether it resulted in an interaction or not. We explore different classification approaches, using different sets of features considering the pose and the motion of the user. We validate and deploy the approach in three scenarios. The first collects 3442 natural sequences (both interacting and non-interacting) representing employees in an office break area: a real-world, challenging setting, where we consider a coffee machine in place of a service robot. The other two scenarios represent researchers interacting with service robots (200 and 72 sequences, respectively). Results show that, even in challenging real-world settings, our approach can learn without external supervision, and can achieve accurate classification (i.e. AUROC greater than 0.9) of the user's intention to interact with an advance of more than 3 s before the interaction actually occurs.
Learning Visual Localization of a Quadrotor using its Noise as Self-Supervision
Mirko Nava, Antonio Paolillo, Jérôme Guzzi, Luca Maria Gambardella, and Alessandro Giusti
in IEEE Robotics and Automation Letters, vol. 7, pp. 2218-2225, 2022.
@article{nava2022learning,
author={M. {Nava} and A. {Paolillo} and J. {Guzzi} and L. M. {Gambardella} and A. {Giusti}},
journal={IEEE Robotics and Automation Letters},
title={Learning Visual Localization of a Quadrotor Using its Noise as Self-Supervision},
year={2022},
volume={7},
number={2},
pages={2218-2225},
doi={10.1109/LRA.2022.3143565}
}
Abstract
We introduce an approach to train neural network models for visual object localization using a small training set, labeled with ground truth object positions, and a large unlabeled one. We assume that the object to be localized emits sound, which is perceived by a microphone rigidly affixed to the camera. This information is used as the target of a cross-modal pretext task: predicting sound features from camera frames. By solving the pretext task, the model draws self-supervision from visual and auditory data. The approach is well suited to robot learning: we instantiate it to localize a small quadrotor from 128x80 pixel images acquired by a ground robot. Experiments on a separate testing set show that introducing the auxiliary pretext task yields large performance improvements: the Mean Absolute Error (MAE) of the estimated image coordinates of the target is reduced from 7 to 4 pixels; the MAE of the estimated distance is reduced from 28 cm to 14 cm. A model that has access to labels for the entire training set yields a MAE of 2 pixels and 11 cm, respectively.
Uncertainty-Aware Self-Supervised Learning of Spatial Perception Tasks
Mirko Nava, Antonio Paolillo, Jérôme Guzzi, Luca Maria Gambardella, and Alessandro Giusti
in IEEE Robotics and Automation Letters, vol. 6, pp. 6693-6700, 2021.
@article{nava2021uncertainty,
author={M. {Nava} and A. {Paolillo} and J. {Guzzi} and L. M. {Gambardella} and A. {Giusti}},
journal={IEEE Robotics and Automation Letters},
title={Uncertainty-Aware Self-Supervised Learning of Spatial Perception Tasks},
year={2021},
volume={6},
number={4},
pages={6693-6700},
doi={10.1109/LRA.2021.3095269}
}
Abstract
We propose a general self-supervised learning approach for spatial perception tasks, such as estimating the pose of an object relative to the robot, from onboard sensor readings. The model is learned from training episodes, by relying on: a continuous state estimate, possibly inaccurate and affected by odometry drift; and a detector, that sporadically provides supervision about the target pose. We demonstrate the general approach in three different concrete scenarios: a simulated robot arm that visually estimates the pose of an object of interest; a small differential drive robot using 7 infrared sensors to localize a nearby wall; an omnidirectional mobile robot that localizes itself in an environment from camera images. Quantitative results show that the approach works well in all three scenarios, and that explicitly accounting for uncertainty yields statistically significant performance improvements.
State-Consistency Loss for Learning Spatial Perception Tasks From Partial Labels
Mirko Nava, Luca Maria Gambardella, and Alessandro Giusti
in IEEE Robotics and Automation Letters, vol. 6, pp. 1112-1119, 2021.
@article{nava2021state,
author={M. {Nava} and L. M. {Gambardella} and A. {Giusti}},
journal={IEEE Robotics and Automation Letters},
title={State-Consistency Loss for Learning Spatial Perception Tasks From Partial Labels},
year={2021},
volume={6},
number={2},
pages={1112-1119},
doi={10.1109/LRA.2021.3056378}
}
Abstract
When learning models for real-world robot spatial perception tasks, one might have access only to partial labels: this occurs for example in semi-supervised scenarios (in which labels are not available for a subset of the training instances) or in some types of self-supervised robot learning (where the robot autonomously acquires a labeled training set, but only acquires labels for a subset of the output variables in each instance). We introduce a general approach to deal with this class of problems using an auxiliary loss enforcing the expectation that the perceived environment state should not abruptly change; then, we instantiate the approach to solve two robot perception problems: a simulated ground robot learning long-range obstacle mapping as a 400-binary-label classification task in a self-supervised way in a static environment; and a real nano-quadrotor learning human pose estimation as a 3-variable regression task in a semi-supervised way in a dynamic environment. In both cases, our approach yields significant quantitative performance improvements (average increase of 6 AUC percentage points in the former; relative improvement of the R 2 metric ranging from 7% to 33% in the latter) over baselines.
Learning Long-Range Perception Using Self-Supervision From Short-Range Sensors and Odometry
Mirko Nava, Jérôme Guzzi, R. Omar Chavez-Garcia, Luca Maria Gambardella and Alessandro Giusti
in IEEE Robotics and Automation Letters, vol. 4, pp. 1279-1286, 2019.
@article{nava2019learning,
author={M. {Nava} and J. {Guzzi} and R. O. {Chavez-Garcia} and L. M. {Gambardella} and A. {Giusti}},
journal={IEEE Robotics and Automation Letters},
title={Learning Long-Range Perception Using Self-Supervision From Short-Range Sensors and Odometry},
year={2019},
volume={4},
number={2},
pages={1279-1286},
doi={10.1109/LRA.2019.2894849}
}
Abstract
We introduce a general self-supervised approach to predict the future outputs of a short-range sensor (such as a proximity sensor) given the current outputs of a long-range sensor (such as a camera). We assume that the former is directly related to some piece of information to be perceived (such as the presence of an obstacle in a given position), whereas the latter is information rich but hard to interpret directly. We instantiate and implement the approach on a small mobile robot to detect obstacles at various distances using the video stream of the robot's forward-pointing camera, by training a convolutional neural network on automatically-acquired datasets. We quantitatively evaluate the quality of the predictions on unseen scenarios, qualitatively evaluate robustness to different operating conditions, and demonstrate usage as the sole input of an obstacle-avoidance controller. We additionally instantiate the approach on a different simulated scenario with complementary characteristics, to exemplify the generality of our contribution.