Search Results for author:
Found 22 papers, 11 papers with code
EgoPet: Egomotion and Interaction Data from an Animal's Perspective
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.
Conformal Policy Learning for Sensorimotor Control Under Distribution Shifts
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.
Learning Vision-based Pursuit-Evasion Robot Policies
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.
Learning Visual Locomotion with Cross-Modal Supervision
In this work, we show how to learn a visual walking policy that only uses a monocular RGB camera and proprioception.
Training Efficient Controllers via Analytic Policy Gradient
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.
Learning a Single Near-hover Position Controller for Vastly Different Quadcopters
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.
Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agents
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.
Learning High-Speed Flight in the Wild
Indeed, the subtasks are executed sequentially, leading to increased processing latency and a compounding of errors through the pipeline.
Jointly Learning Identification and Control for Few-Shot Policy Adaptation
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.
AutoTune: Controller Tuning for High-Speed Flight
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.
Primal-Dual Mesh Convolutional Neural Networks
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.
Flightmare: A Flexible Quadrotor Simulator
State-of-the-art quadrotor simulators have a rigid and highly-specialized structure: either are they really fast, physically accurate, or photo-realistic.
Deep Drone Acrobatics
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
Event-based Asynchronous Sparse Convolutional Networks
However, these approaches discard the spatial and temporal sparsity inherent in event data at the cost of higher computational complexity and latency.
Learning Depth With Very Sparse Supervision
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.
Global-Local Network for Learning Depth with Very Sparse Supervision
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.
A General Framework for Uncertainty Estimation in Deep Learning
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.
End-to-End Learning of Representations for Asynchronous Event-Based Data
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
Unsupervised Moving Object Detection via Contextual Information Separation
We propose an adversarial contextual model for detecting moving objects in images.
A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones
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.
Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars
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
Computational Eco-Systems for Handwritten Digits Recognition
Inspired by the importance of diversity in biological system, we built an heterogeneous system that could achieve this goal.
