Portrait de Inna Sharf

Inna Sharf

Membre affilié
Professeur titulaire, McGill University, Département de mécanique
Sujets de recherche
Robotique
Site web
Google Scholar

Publications

Vision-Based Semantic SLAM for Autonomous Navigation in Mill Yard
Junrui Huang
Inna Sharf
Elie Ayoub
Nicolas Lemieux
Heshan Fernando
Log-loading machines are essential in mill-yard operations for unloading logs from incoming transport trucks onto mill infeed deck, as well … (voir plus)as managing log inventory in stockpiles. This paper focuses on the log-loading operation in the vicinity of the infeed deck, with the goal of enabling higher levels of autonomy in this task. Near the infeed deck, the machine must localize reliably relative to the infeed deck and adjacent buffer piles, while also detecting and localizing arriving trucks and trailers; this is a highly dynamic outdoor environment. We present a vision-based semantic SLAM system that uses a stereo camera mounted on the log-loading machine as the sole perception sensor. The proposed pipeline is based on stereo ORB-SLAM2 for real-time pose estimation and mapping. It integrates a parallel semantic thread that converts stereo depth into pseudo-LiDAR point clouds and predicts oriented 3D bounding boxes for key objects, including the infeed deck, log piles, and log trucks. The estimated 3D bounding boxes are used to remove features on potentially dynamic objects during SLAM tracking for improving robustness, and to construct a persistent object-level semantic map by transforming 3D bounding boxes into the global SLAM frame. We evaluated the system in a virtual NVIDIA Isaac Sim infeed-deck environment using synthetic stereo image sequences. The evaluation reports camera trajectory accuracy, semantic object localization accuracy, and runtime performance, and includes ablations to isolate the impact of dynamic-feature removal and object-level semantic mapping. The results indicate that incorporating object-level 3D detections improves the robustness and accuracy of stereo SLAM in dynamic infeed-deck scenes while producing a globally consistent semantic map in practical runtime.
2026-05-13
Conference on Robots and Vision (publié)
doi.org
Resonant Motion of Echo I: A Case Study of SRP and $$J_2$$ Coupling
Catherine Massé
Inna Sharf
2026-03-02
Journal of the Astronautical Sciences (publié)
doi.org
Path Following Guidance Strategy for Autonomous Dynamic Soaring
Zihao Zhuo
Meyer Nahon
Inna Sharf
Dynamic soaring is a flight mode that harvests energy from the vertical gradient of horizontal wind and can be used to increase the enduranc… (voir plus)e and range of unmanned aerial vehicles. Previous studies have mainly focused on trajectory optimization for dynamic soaring, while the problem of following these optimal paths with an autonomous glider has received limited attention. This study proposes a novel guidance strategy that enables precise tracking of an optimal dynamic soaring path on an autonomous glider vehicle. The proposed guidance strategy combines a geometric path-following guidance law with a command projection module specifically designed to address the unique challenges of dynamic soaring, such as the presence of crosswind components and the underactuated nature of glider vehicles. The performance of the proposed guidance strategy is demonstrated through numerical simulations of a 2 m wingspan glider executing dynamic soaring maneuvers in both ridge and surface wind shear layers.
2026-01-07
AIAA Science and Technology Forum and Exposition (publié)
doi.org
Designing Experimental Setup Emulating Log-Loader Manipulator and Implementing Anti-Sway Trajectory Planner
Iman Jebellat
George Sideris
Rafid Saif
Inna Sharf
Forestry machines are not easily accessible for experimentation or demonstration of research results. These mobile robots are massive, very … (voir plus)expensive, and require a large outdoor space and permits to operate. These factors hinder conducting experiments on real forestry robots. Thus, it is essential to design experimental setups utilizing easily accessible robots in indoor labs that can effectively replicate the behavior of interest of a forestry machine. We design a setup to resemble a log-loader crane and grapple motions using a Kinova Jaco2 arm by manufacturing a specialized end-effector to attach passively to the Jaco2 arm. Passively attached grapple causes undesirable sway, which is problematic and dangerous in forestry. To address the sway problem, we employ dynamic programming to develop an anti-sway motion planner, and validate its performance for different point-to-point maneuvers in our experimental setup. We also repeat each experiment at least 6 times to ensure the repeatability and reliability of the experiments. The experimental results showcase the excellent sway-damping performance of our planner and also the very good repeatability of our experiments.
2024-12-31
IEEE International Conference on Robotics and Automation (publié)
doi.org
Learning the Latent Space of Robot Dynamics for Cutting Interaction Inference
Sahand Rezaei-Shoshtari
David Meger
Inna Sharf
Utilization of latent space to capture a lower-dimensional representation of a complex dynamics model is explored in this work. The targeted… (voir plus) application is of a robotic manipulator executing a complex environment interaction task, in particular, cutting a wooden object. We train two flavours of Variational Autoencoders---standard and Vector-Quantised---to learn the latent space which is then used to infer certain properties of the cutting operation, such as whether the robot is cutting or not, as well as, material and geometry of the object being cut. The two VAE models are evaluated with reconstruction, prediction and a combined reconstruction/prediction decoders. The results demonstrate the expressiveness of the latent space for robotic interaction inference and the competitive prediction performance against recurrent neural networks.
2021-01-23
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publié)
doi.org
arxiv.org
Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning
Sahand Rezaei-Shoshtari
David Meger
Inna Sharf
Motivated by the recursive Newton-Euler formulation, we propose a novel cascaded Gaussian process learning framework for the inverse dynamic… (voir plus)s of robot manipulators. This approach leads to a significant dimensionality reduction which in turn results in better learning and data efficiency. We explore two formulations for the cascading: the inward and outward, both along the manipulator chain topology. The learned modeling is tested in conjunction with the classical inverse dynamics model (semi-parametric) and on its own (non-parametric) in the context of feed-forward control of the arm. Experimental results are obtained with Jaco 2 six-DOF and SARCOS seven-DOF manipulators for randomly defined sinusoidal motions of the joints in order to evaluate the performance of cascading against the standard GP learning. In addition, experiments are conducted using Jaco 2 on a task emulating a pouring maneuver. Results indicate a consistent improvement in learning speed with the inward cascaded GP model and an overall improvement in data efficiency and generalization.
2019-11-02
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publié)
doi.org
arxiv.org