5 accepted papers
Reinforcement Learning with Verifiable Rewards (RLVR) for Multimodal Large Language Models (MLLMs) is highly dependent on high-quality labeled data, which is often scarce and prone to substantial annotation noise in real-world scenarios. Existing unsupervised RLVR methods, including pure entropy min
Accurate pedestrian navigation on edge devices is a critical problem. While artificial neural networks (ANNs) have been shown to effectively solve this problem with acceptable accuracy, their energy consumption limits applications on low-power computation platforms. Spiking neural networks (SNNs) ar…
This paper develops an adaptive integral sliding mode control scheme to manipulate the cable-driven robots, realizing robust parallel cooperation performance for the variable loads. The considered cable-driven robot system (CDRS) employs multiple flexible cables to cooperatively regulate the robotic
This paper focuses on target-oriented grasping in occluded scenes, where the target object is specified by a binary mask and the goal is to grasp the target object with as few robotic manipulations as possible. Most existing methods rely on a push-grasping synergy to complete this task. To deliver a…
This letter investigates the direct trajectory optimization of the free-floating space manipulator (FFSM). The main purpose is to plan the joint space trajectories to reduce the spacecraft motion due to the joint rotation during the FFSM performing tasks. To improve the calculation efficiency, the a