In human-robot collaboration (HRC) settings, hand motion intention prediction (HMIP) plays a pivotal role in ensuring prompt decision-making, safety, and an intuitive collaboration experience. Precise and robust HMIP with low computational resources remains a challenge due to the stochastic nature of hand motion and the diversity of HRC tasks. This paper proposes a framework that combines hand trajectories and gaze data to foster robust, real-time HMIP with minimal to no training. A novel 3D vector field method is introduced for hand trajectory representation, leveraging minimum jerk trajectory predictions to discern potential hand motion endpoints. This is statistically combined with gaze fixation data using a weighted Naive Bayes Classifier (NBC). Acknowledging the potential variances in saccadic eye motion due to factors like fatigue or inattentiveness, we incorporate stationary gaze entropy to gauge visual concentration, thereby adjusting the contribution of gaze fixation to the HMIP. Empirical experiments substantiate that the proposed framework robustly predicts intended endpoints of hand motion before at least 50% of the trajectory is completed. It also successfully exploits gaze fixations when the human operator is attentive and mitigates its influence when the operator loses focus. A real-time implementation in a construction HRC scenario (collaborative tiling) showcases the intuitive nature and potential efficiency gains to be leveraged by introducing the proposed HMIP into HRC contexts. The opens-ource implementation of the framework is made available at https://github.com/maleenj/hmip_ros.git.

In the state-of-the-art approaches to SLAM, the problem is often formulated as a non-linear least squares. SLAM back-ends often employ iterative methods such as Gauss-Newton or Levenberg-Marquardt to solve that problem. In general, there is no guarantee on the global convergence of these methods. The back-end might get trapped into a local minimum or even diverge depending on how good the initial estimate is. Due to the large noise in odometry data, it is not wise to rely on dead reckoning for obtaining an initial guess, especially in long trajectories. In this paper we demonstrate how M-estimation can be used as a bootstrapping technique to obtain a reliable initial guess. We show that this initial guess is more likely to be in the basin of attraction of the global minimum than existing bootstrapping methods. As the main contribution of this paper, we present new insights about the similarities between robustness against outliers and robustness against a bad initial guess. Through simulations and experiments on real data, we substantiate the reliability of our proposed method.

Recently RGB-D sensors have become very popular in the area of Simultaneous Localisation and Mapping (SLAM). The major advantage of these sensors is that they provide a rich source of 3D information at relatively low cost. Unfortunately, these sensors in their current forms only have a range accuracy of up to 4 metres. Many techniques which perform SLAM using RGB-D cameras rely heavily on the depth and are restrained to office type and geometrically structured environments. In this paper, a switching based algorithm is proposed to heuristically choose between RGB-BA and RGBD-BA based local maps building. Furthermore, a low cost and consistent optimisation approach is used to join these maps. Thus the potential of both RGB and depth image information are exploited to perform robust SLAM in more general indoor cases. Validation of the proposed algorithm is performed by mapping a large scale indoor scene where traditional RGB-D mapping techniques are not possible.

This paper first demonstrates an interesting property of bundle adjustment (BA), “scale drift correction”. Here “scale drift correction” means that BA can converge to the correct solution (up to a scale) even if the initial values of the camera pose translations and point feature positions are calculated using very different scale factors. This property together with other properties of BA makes it the best approach for monocular Simultaneous Localization and Mapping (SLAM), without considering the computational complexity. This naturally leads to the idea of using local BA and map joining to solve large-scale monocular SLAM problem, which is proposed in this paper. The local maps are built through Scale-Invariant Feature Transform (SIFT) for feature detection and matching, random sample consensus (RANSAC) paradigm at different levels for robust outlier removal, and BA for optimization. To reduce the computational cost of the large-scale map building, the features in each local map are judiciously selected and then the local maps are combined using a recently developed 3D map joining algorithm. The proposed large-scale monocular SLAM algorithm is evaluated using a publicly available dataset with centimeter-level ground truth.

In recent SLAM (simultaneous localization and mapping) literature, Pose Only optimization methods have become increasingly popular. This is greatly supported by the fact that these algorithms are computationally more efficient, as they focus more on the robots trajectory rather than dealing with a complex map. Implementation simplicity allows these to handle both 2D and 3D environments with ease. This paper presents a detailed evaluation on the reliability and accuracy of Pose Only SLAM, and aims at providing a definitive answer to whether optimizing poses is more advantages than optimizing features. Focus is centered around TORO, a Tree based network optimization algorithm, which has gained increased recognition within the robotics community. We compare this with Least Squares, which is often considered one of the best Maximum Likelihood method available. Results are based on both simulated and real 2D environments, and presented in a way where our conclusions can be substantiated.