A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots

By Alessandro Giusti, Jérôme Guzzi, Dan Claudiu Ciresan, Fangwei He, Juan P. Rodriguez, Flavio Fontana, Matthias Faessler, Christian Forster, J. Urgen Schmidhuber, Gianni Di Caro and 2 more. 2016

688 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Environmental Engineering, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Environmental Engineering

In Robotics & Control

Citations in the corpus

Value Iteration Networks (2016, methodology): “ntial nature of decision making in RL is inherently different than the one-step decisions in supervised learning, and in general requires some form of planning [3]. However, most recent deep RL works [19, 16, 10] employed NN architectures that are very similar to the standard networks used in superv”
A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, positive): “Giusti et al. (2016) train a deep network to determine actions that can keep a quadrotor on a trail, by learning on single monocular images collected from the robot’s perspective.”
Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing (2018, background): “Output representations range from predicting discrete navigation commands (classification in action space) [11], [7], [15] to direct regression of control signals [19].”
Learning to Drive in a Day (2018, background): “Variants of this approach have been demonstrated on self-driving cars [18], [19] and drones [20], [21], [22].”
End-to-End Driving Via Conditional Imitation Learning (2017, background): “Imitation learning has been applied to a variety of tasks, including articulated motion [2], [28], [11], autonomous flight [1], [13], [30], modeling navigational behavior [37], [38], off-road driving [22], [32], and road following [4], [6], [27], [36].”
(CAD)$^2$RL: Real Single-Image Flight without a Single Real Image (2016, methodology): “This is in contrast to the prior work, which simply predicts the action that will cause the vehicle to follow a trail [14].”
Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation (2017, background): “This approach has proven successful in domains where collecting such demonstrations is natural, such as simulated environments [24], [35], driving [4], [5], [6], and drones [36].”
One-Shot Visual Imitation Learning via Meta-Learning (2017, background): “Imitation learning from raw pixels has been widely studied in the context of mobile robotics [12, 13, 14, 15].”
Overcoming Exploration in Reinforcement Learning with Demonstrations (2017, background): “BC has seen success in autonomous driving [5], [6], quadcopter navigation [7], locomotion [8], [9].”
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey (2018, background): “self driving cars [12], [180], surveillance [13], maleware detection [34], [107], drones and robotics [155], [178], and voice command recognition [7].”
Safe Visual Navigation via Deep Learning and Novelty Detection (2017, background): “While we focus on supervised learning of collision probability, there are many other ways to map between images and actions, including end-to-end neural networks [6, 19], affordance-based representations [7], reinforcement learning using either simulated or real images [23, 31], and classification o”
PLATO: Policy learning using adaptive trajectory optimization (2016, background): “Recent years have seen considerable research on using deep networks for control [2], [3], [4], [5], [6], [7].”
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos (2022, background): “Imitation learning is simplest when demonstrations are labeled with corresponding actions Imitating labeled trajectories has seen success in aerial vehicles, 40,41 self-driving cars, 42,43 board games, 10,44 and video games.”
An Exploration of Embodied Visual Exploration (2020, methodology): “We first pre-train the exploration policy via imitation learning (Bojarski et al. 2016; Giusti et al. 2016).”
Toward low-flying autonomous MAV trail navigation using deep neural networks for environmental awareness (2017, methodology): “We first trained a 3-category DNN to predict view orientation (left / center / right), see Figure 3, using the IDSIA Swiss Alps trail dataset available from [13].”
Guided Meta-Policy Search (2019, positive): “…learning algorithms and RL algorithms that leverage supervised learning have been far more successful (Levine et al., 2016; Bojarski et al., 2016; Giusti et al., 2016; Zhang & Cho, 2017), which can largely be attributed to the stability of supervised learning as compared with reinforcement…”
A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles (2017, methodology): “With regard to UAV navigation in unstructured environments, some studies have focused on cluttered natural scenarios, such as dense forests or trails [40].”