Exteroceptive Perception

Exteroceptive perception, the ability of a system to sense its external environment, is a crucial area of research in robotics and autonomous systems. Current efforts focus on improving the robustness and efficiency of exteroceptive sensing, particularly in challenging conditions, using various approaches including deep reinforcement learning (DRL) with variational autoencoders (VAEs) for data compression, attention-based recurrent neural networks for multimodal data fusion, and central pattern generators (CPGs) integrated with DRL for locomotion control. These advancements are driving progress in areas such as autonomous navigation, human-robot interaction, and manipulation of deformable objects, with significant implications for the development of more capable and adaptable robots.

Papers

November 11, 2024

Proprioceptive and Exteroceptive Information Perception in a Fabric Soft Robotic Arm via Physical Reservoir Computing with minimal training data
Jun Wang, Zhi Qiao, Wenlong Zhang, Suyi Li
Training Data Robotic Arm Soft Pneumatic Actuator Physical Reservoir Computing Exteroceptive Perception

September 11, 2024

Robust Robot Walker: Learning Agile Locomotion over Tiny Traps
Shaoting Zhu, Runhan Huang, Linzhan Mou, Hang Zhao
Quadruped Robot Agile Locomotion Field Trap Exteroceptive Perception Proprioceptive Input Robust Walking

August 2, 2024

EVIT: Event-based Visual-Inertial Tracking in Semi-Dense Maps Using Windowed Nonlinear Optimization
Runze Yuan, Tao Liu, Zijia Dai, Yi-Fan Zuo, Laurent Kneip
Event Camera Dense Mapping Nonlinear Programming Cooperative Target Tracking Exteroceptive Perception Modality Registration Event Based Visual Inertial

June 22, 2024

XBG: End-to-end Imitation Learning for Autonomous Behaviour in Human-Robot Interaction and Collaboration
Carlos Cardenas-Perez, Giulio Romualdi, Mohamed Elobaid, Stefano Dafarra, Giuseppe L'Erario, Silvio Traversaro, Pietro Morerio, Alessio Del Bue, Daniele Pucci
Imitation Learning Human Robot Interaction Humanoid Robot Autonomous Behavior Exteroceptive Perception

March 31, 2024

Variational Autoencoders for exteroceptive perception in reinforcement learning-based collision avoidance
Thomas Nakken Larsen, Eirik Runde Barlaug, Adil Rasheed
Deep Reinforcement Learning Variational Autoencoders Collision Avoidance Positive Reinforcement Autonomous Vessel Exteroceptive Perception Autonomous Underwater

March 18, 2024

EffiPerception: an Efficient Framework for Various Perception Tasks
Xinhao Xiang, Simon Dräger, Jiawei Zhang
3D Object Detection Segmentation Task Vision Task Efficient Framework 2 Dimensional Object Detection Perception Task Accuracy Tradeoff Exteroceptive Perception

April 14, 2023

Learning Perceptive Bipedal Locomotion over Irregular Terrain
Bart van Marum, Matthia Sabatelli, Hamidreza Kasaei
Proprioceptive Sensing Quadrupedal Locomotion Bipedal Walking Uneven Terrain Perceptive Locomotion Exteroceptive Perception

April 5, 2023

Flipbot: Learning Continuous Paper Flipping via Coarse-to-Fine Exteroceptive-Proprioceptive Exploration
Chao Zhao, Chunli Jiang, Junhao Cai, Michael Yu Wang, Hongyu Yu, Qifeng Chen
Deformable Object Real Robot Coarse to Fine Exteroceptive Perception

December 29, 2022

Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotion
Guillaume Bellegarda, Milad Shafiee, Auke Ijspeert
Proprioceptive Sensing Robust Navigation Central Pattern Generator Perceptive Locomotion Exteroceptive Perception Robust Gait

September 28, 2022

Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping
Victor R. F. Miranda, Armando A. Neto, Gustavo M. Freitas, Leonardo A. Mozelli
Deep Reinforcement Learning Strong Generalization Collision Avoidance Robot Navigation Reward Shaping DRL Algorithm Exteroceptive Perception COLlision Avoidance

July 7, 2022

Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning
Lu Gan, Jessy W. Grizzle, Ryan M. Eustice, Maani Ghaffari
Inverse Reinforcement Learning Terrain Traversability Exteroceptive Perception Deep Inverse Reinforcement Learning

April 27, 2022

Memory based neural networks for end-to-end autonomous driving
Sergio Paniego Blanco, Sakshay Mahna, Utkarsh A. Mishra, JoseMaria Canas
Neural Network Autonomous Driving End to End Memory Trace Exteroceptive Perception

January 20, 2022

Learning robust perceptive locomotion for quadrupedal robots in the wild
Takahiro Miki, Joonho Lee, Jemin Hwangbo, Lorenz Wellhausen, Vladlen Koltun, Marco Hutter
LeArning Abstract Legged Robot Quadrupedal Robot Legged Locomotion Proprioceptive Sensing Multiple Gait Perceptive Locomotion Exteroceptive Perception

November 30, 2021

ARTSeg: Employing Attention for Thermal images Semantic Segmentation
Farzeen Munir, Shoaib Azam, Unse Fatima, Moongu Jeon
Autonomous Vehicle Human Attention Thermal Image Thermal Camera Exteroceptive Perception Thermal Semantic Segmentation

Exteroceptive Perception

Papers

Proprioceptive and Exteroceptive Information Perception in a Fabric Soft Robotic Arm via Physical Reservoir Computing with minimal training data

Robust Robot Walker: Learning Agile Locomotion over Tiny Traps

EVIT: Event-based Visual-Inertial Tracking in Semi-Dense Maps Using Windowed Nonlinear Optimization

XBG: End-to-end Imitation Learning for Autonomous Behaviour in Human-Robot Interaction and Collaboration

Variational Autoencoders for exteroceptive perception in reinforcement learning-based collision avoidance

EffiPerception: an Efficient Framework for Various Perception Tasks

Learning Perceptive Bipedal Locomotion over Irregular Terrain

Flipbot: Learning Continuous Paper Flipping via Coarse-to-Fine Exteroceptive-Proprioceptive Exploration

Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotion

Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping

Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning

Memory based neural networks for end-to-end autonomous driving

Learning robust perceptive locomotion for quadrupedal robots in the wild

ARTSeg: Employing Attention for Thermal images Semantic Segmentation