23+ hour, 17+ min ago   (678+ words) Mapless deep reinforcement learning (DRL) navigation in dynamic indoor environments is difficult under single-frame 2D LiDAR, which reports where an obstacle is but not whether it is approaching. We introduce the Positional-Velocity Spatio-Temporal Attention Module (PV-STAM), a compact perception block (19,968 trainable…...

1+ week, 2+ day ago   (428+ words) Space-constrained articulated mechanisms integrated into mechatronic assemblies require rigorous kinematic characterisation during preliminary design, since spatial limitations and the avoidance of kinematic locking in the transient regime constrain the admissible geometry. An original planar guidance-and-retraction linkage is analysed, composed of…...

1+ week, 3+ day ago   (297+ words) Robot Operating System (ROS) applications are growing increasingly complex and distributed, incorporating multi-node architectures, real-time communication, and compute offloading to cloud or edge resources. Despite advances in containerization, large-scale robotics deployments often rely on ad hoc provisioning, updating, and scalability…...

1+ week, 5+ day ago   (411+ words) This paper proposes a hybrid machine-learning approach based on the genetic-neural online adaptation of the process noise covariance matrix in an adaptive Kalman filter, designed to improve the accuracy of dynamic tracking in electro-pneumatic systems. The method combines offline parameter…...

2+ week, 2+ day ago   (495+ words) Conditional imitation learning (CIL) for CARLA depends on diverse expert data spanning map, weather, traffic, and control-perturbation axes, yet it remains unclear which axes actually drive closed-loop behavior, and whether ablation conclusions survive deployment guardrails. We train a matched baseline and…...

3+ week, 1+ day ago   (410+ words) Improving sample efficiency and achieving balanced multi-task performance across different tasks remain important research challenges in reinforcement learning. Yie Ar Kung-Fu is formulated as a multi-task reinforcement learning environment. A task-specific neural network architecture, simplified state and action encoding schemes,…...

3+ week, 1+ day ago   (458+ words) In industrial robot trajectory planning, trajectory segmentation has crucial importance in distinguishing between different geometric primitives, such as straight lines and arcs. Separating these elements facilitates allocating optimized motion instructions, customized to each segment category. This distinction ensures both improved…...

3+ week, 1+ day ago   (625+ words) This study investigated the application of Covariant Hamiltonian Optimization for Motion Planning (CHOMP) in the MATLAB programming environment to an industrially relevant Universal Robots UR5e six-DOF manipulator. The parameters were set to be equal to those of the standard MoveIt2 CHOMP plugin,…...

3+ week, 4+ day ago   (392+ words) Robot-centric elevation maps built from onboard sensing are always incomplete: occlusions, a limited field of view, and range limits leave large unobserved regions that traversability analysis and motion planning must still reason about. We present a supervised framework that completes…...

3+ week, 5+ day ago   (731+ words) The increasing complexity of cyber–physical manufacturing systems demands simulation architectures that scale with the physical plant without a proportional growth in engineering effort. This paper introduces a formal, symmetry-based framework for behavioral reuse in arbitrary cyber–physical manufacturing systems,…...