References of "IEEE Robotics and Automation Letters"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailStriving for Less: Minimally-Supervised Pseudo-Label Generation for Monocular Road Segmentation
Robinet, François UL; Akl, Yussef UL; Ullah, Kaleem UL et al

in IEEE Robotics and Automation Letters (2022), 7(4), 10628-10634

Identifying traversable space is one of the most important problems in autonomous robot navigation and is primarily tackled using learning-based methods. To alleviate the prohibitively high annotation ... [more ▼]

Identifying traversable space is one of the most important problems in autonomous robot navigation and is primarily tackled using learning-based methods. To alleviate the prohibitively high annotation-cost associated with labeling large and diverse datasets, research has recently shifted from traditional supervised methods to focus on unsupervised and semi-supervised approaches. This work focuses on monocular road segmentation and proposes a practical, generic, and minimally-supervised approach based on task-specific feature extraction and pseudo-labeling. Building on recent advances in monocular depth estimation models, we process approximate dense depth maps to estimate pixel-wise road-plane distance maps. These maps are then used in both unsupervised and semi-supervised road segmentation scenarios. In the unsupervised case, we propose a pseudo-labeling pipeline that reaches state-of-the-art Intersection-over-Union (IoU), while reducing complexity and computations compared to existing approaches. We also investigate a semi-supervised extension to our method and find that even minimal labeling efforts can greatly improve results. Our semi-supervised experiments using as little as 1% and 10% of ground truth data, yield models scoring 0.9063 and 0.9332 on the IoU metric respectively. These results correspond to a comparative performance of 95.9% and 98.7% of a fully-supervised model's IoU score, which motivates a pragmatic approach to labeling. [less ▲]

Detailed reference viewed: 34 (6 UL)
Full Text
Peer Reviewed
See detailEnhancing Rover Teleoperation on the Moon With Proprioceptive Sensors and Machine Learning Techniques
Coloma Chacon, Sofia UL; Martinez Luna, Carol UL; Yalcin, Baris Can UL et al

in IEEE Robotics and Automation Letters (2022)

Geological formations, environmental conditions, and soil mechanics frequently generate undesired effects on rovers’ mobility, such as slippage or sinkage. Underestimating these undesired effects may ... [more ▼]

Geological formations, environmental conditions, and soil mechanics frequently generate undesired effects on rovers’ mobility, such as slippage or sinkage. Underestimating these undesired effects may compromise the rovers’ operation and lead to a premature end of the mission. Minimizing mobility risks becomes a priority for colonising the Moon and Mars. However, addressing this challenge cannot be treated equally for every celestial body since the control strategies may differ; e.g. the low latency EarthMoon communication allows constant monitoring and controls, something not feasible on Mars. This letter proposes a Hazard Information System (HIS) that estimates the rover’s mobility risks (e.g. slippage) using proprioceptive sensors and Machine Learning (supervised and unsupervised). A Graphical User Interface was created to assist human-teleoperation tasks by presenting mobility risk indicators. The system has been developed and evaluated in the lunar analogue facility (LunaLab) at the University of Luxembourg. A real rover and eight participants were part of the experiments. Results demonstrate the benefits of the HIS in the decision-making processes of the operator’s response to overcome hazardous situations. [less ▲]

Detailed reference viewed: 70 (18 UL)
Full Text
Peer Reviewed
See detailA Real-Time Approach for Chance-Constrained Motion Planning with Dynamic Obstacles
Castillo Lopez, Manuel UL; Ludivig, Philippe; Sajadi-Alamdari, Seyed Amin et al

in IEEE Robotics and Automation Letters (2020), 5(2), 3620-3625

Uncertain dynamic obstacles, such as pedestrians or vehicles, pose a major challenge for optimal robot navigation with safety guarantees. Previous work on motion planning has followed two main strategies ... [more ▼]

Uncertain dynamic obstacles, such as pedestrians or vehicles, pose a major challenge for optimal robot navigation with safety guarantees. Previous work on motion planning has followed two main strategies to provide a safe bound on an obstacle's space: a polyhedron, such as a cuboid, or a nonlinear differentiable surface, such as an ellipsoid. The former approach relies on disjunctive programming, which has a relatively high computational cost that grows exponentially with the number of obstacles. The latter approach needs to be linearized locally to find a tractable evaluation of the chance constraints, which dramatically reduces the remaining free space and leads to over-conservative trajectories or even unfeasibility. In this work, we present a hybrid approach that eludes the pitfalls of both strategies while maintaining the original safety guarantees. The key idea consists in obtaining a safe differentiable approximation for the disjunctive chance constraints bounding the obstacles. The resulting nonlinear optimization problem is free of chance constraint linearization and disjunctive programming, and therefore, it can be efficiently solved to meet fast real-time requirements with multiple obstacles. We validate our approach through mathematical proof, simulation and real experiments with an aerial robot using nonlinear model predictive control to avoid pedestrians. [less ▲]

Detailed reference viewed: 320 (35 UL)