no code implementations • 15 Apr 2024 • Amir Bar, Arya Bakhtiar, Danny Tran, Antonio Loquercio, Jathushan Rajasegaran, Yann Lecun, Amir Globerson, Trevor Darrell
Animals perceive the world to plan their actions and interact with other agents to accomplish complex tasks, demonstrating capabilities that are still unmatched by AI systems.
no code implementations • 2 Nov 2023 • Huang Huang, Satvik Sharma, Antonio Loquercio, Anastasios Angelopoulos, Ken Goldberg, Jitendra Malik
The key idea is the design of switching policies that can take conformal quantiles as input, which we define as conformal policy learning, that allows robots to detect distribution shifts with formal statistical guarantees.
no code implementations • 30 Aug 2023 • Andrea Bajcsy, Antonio Loquercio, Ashish Kumar, Jitendra Malik
We find that the quality of the supervision signal for the partially-observable pursuer policy depends on two key factors: the balance of diversity and optimality of the evader's behavior and the strength of the modeling assumptions in the fully-observable policy.
no code implementations • 7 Nov 2022 • Antonio Loquercio, Ashish Kumar, Jitendra Malik
In this work, we show how to learn a visual walking policy that only uses a monocular RGB camera and proprioception.
1 code implementation • 26 Sep 2022 • Nina Wiedemann, Valentin Wüest, Antonio Loquercio, Matthias Müller, Dario Floreano, Davide Scaramuzza
Conversely, learning-based offline optimization approaches, such as Reinforcement Learning (RL), allow fast and efficient execution on the robot but hardly match the accuracy of MPC in trajectory tracking tasks.
no code implementations • 19 Sep 2022 • Dingqi Zhang, Antonio Loquercio, Xiangyu Wu, Ashish Kumar, Jitendra Malik, Mark W. Mueller
This paper proposes an adaptive near-hover position controller for quadcopters, which can be deployed to quadcopters of very different mass, size and motor constants, and also shows rapid adaptation to unknown disturbances during runtime.
no code implementations • 7 Jan 2022 • Christian Pfeiffer, Simon Wengeler, Antonio Loquercio, Davide Scaramuzza
This work investigates whether neural networks capable of imitating human eye gaze behavior and attention can improve neural network performance for the challenging task of vision-based autonomous drone racing.
1 code implementation • 11 Oct 2021 • Antonio Loquercio, Elia Kaufmann, René Ranftl, Matthias Müller, Vladlen Koltun, Davide Scaramuzza
Indeed, the subtasks are executed sequentially, leading to increased processing latency and a compounding of errors through the pipeline.
no code implementations • 29 Sep 2021 • Nina Wiedemann, Antonio Loquercio, Matthias Müller, Rene Ranftl, Davide Scaramuzza
We evaluate our approach on several complex systems and tasks, and experimentally analyze the advantages over model-free and model-based methods in terms of performance and sample efficiency.
1 code implementation • 19 Mar 2021 • Antonio Loquercio, Alessandro Saviolo, Davide Scaramuzza
To answer the first question, we study the relationship between parameters and performance and find out that the faster the maneuver, the more sensitive a controller becomes to its parameters.
1 code implementation • NeurIPS 2020 • Francesco Milano, Antonio Loquercio, Antoni Rosinol, Davide Scaramuzza, Luca Carlone
Recent works in geometric deep learning have introduced neural networks that allow performing inference tasks on three-dimensional geometric data by defining convolution, and sometimes pooling, operations on triangle meshes.
3 code implementations • 1 Sep 2020 • Yunlong Song, Selim Naji, Elia Kaufmann, Antonio Loquercio, Davide Scaramuzza
State-of-the-art quadrotor simulators have a rigid and highly-specialized structure: either are they really fast, physically accurate, or photo-realistic.
1 code implementation • 10 Jun 2020 • Elia Kaufmann, Antonio Loquercio, René Ranftl, Matthias Müller, Vladlen Koltun, Davide Scaramuzza
In this paper, we propose to learn a sensorimotor policy that enables an autonomous quadrotor to fly extreme acrobatic maneuvers with only onboard sensing and computation.
Robotics
1 code implementation • ECCV 2020 • Nico Messikommer, Daniel Gehrig, Antonio Loquercio, Davide Scaramuzza
However, these approaches discard the spatial and temporal sparsity inherent in event data at the cost of higher computational complexity and latency.
no code implementations • 2 Mar 2020 • Antonio Loquercio, Alexey Dosovitskiy, Davide Scaramuzza
Motivated by the astonishing capabilities of natural intelligent agents and inspired by theories from psychology, this paper explores the idea that perception gets coupled to 3D properties of the world via interaction with the environment.
no code implementations • 25 Sep 2019 • Antonio Loquercio, Alexey Dosovitskiy, Davide Scaramuzza
Natural intelligent agents learn to perceive the three dimensional structure of the world without training on large datasets and are unlikely to have the precise equations of projective geometry hard-wired in the brain.
1 code implementation • 16 Jul 2019 • Antonio Loquercio, Mattia Segù, Davide Scaramuzza
Current approaches for uncertainty estimation of neural networks require changes to the network and optimization process, typically ignore prior knowledge about the data, and tend to make over-simplifying assumptions which underestimate uncertainty.
1 code implementation • ICCV 2019 • Daniel Gehrig, Antonio Loquercio, Konstantinos G. Derpanis, Davide Scaramuzza
Event cameras are vision sensors that record asynchronous streams of per-pixel brightness changes, referred to as "events".
Ranked #15 on Robust classification on N-ImageNet
1 code implementation • CVPR 2019 • Yanchao Yang, Antonio Loquercio, Davide Scaramuzza, Stefano Soatto
We propose an adversarial contextual model for detecting moving objects in images.
3 code implementations • 4 May 2018 • Daniele Palossi, Antonio Loquercio, Francesco Conti, Eric Flamand, Davide Scaramuzza, Luca Benini
As part of our general methodology we discuss the software mapping techniques that enable the state-of-the-art deep convolutional neural network presented in [1] to be fully executed on-board within a strict 6 fps real-time constraint with no compromise in terms of flight results, while all processing is done with only 64 mW on average.
no code implementations • CVPR 2018 • Ana I. Maqueda, Antonio Loquercio, Guillermo Gallego, Narciso Garcia, Davide Scaramuzza
Event cameras are bio-inspired vision sensors that naturally capture the dynamics of a scene, filtering out redundant information.
Ranked #12 on Robust classification on N-ImageNet
no code implementations • 6 Mar 2017 • Antonio Loquercio, Francesca Della Torre, Massimo Buscema
Inspired by the importance of diversity in biological system, we built an heterogeneous system that could achieve this goal.