We thank the reviewers for their valuable feedback and comments. R3 & R5 point out that parts of some modules are based on prior work. Novelty is also recognized by R1 ("clear algorithmic innovation") and R2 ("adds several new features"). All reviewers have appreciated the real-world experiments in the submission. R1 & R5 have suggested there should be more emphasis on real-world experiments.

Abstract-- We demonstrate real-time high-altitude aerial metric-semantic mapping and exploration using a monocular camera paired with a global positioning system (GPS) and an inertial measurement unit (IMU). Our system, named HALO, addresses two key challenges: (i) real-time dense 3D reconstruction using vision at large distances, and (ii) mapping and exploration of large-scale outdoor environments with accurate scene geometry and semantics. We demonstrate that HALO can plan informative paths that exploit this information to complete missions with multiple tasks specified in natural language. We use real-world experiments on a custom quadrotor platform to demonstrate that (i) all modules can run onboard the robot, and that (ii) in diverse environments HALO can support effective autonomous execution of missions covering up to 24,600 sq. Experiment videos and more details can be found on our project page: https://tyuezhan.github. Aerial robots operating at high altitudes have a large effective field-of-view, this can be used very effectively for mapping and exploration. However, high-altitude aerial operations present some unusual challenges in perception. For example, consumer-grade LiDARs provide accurate depth but the point density at large distances is low. LiDARs are also expensive, heavy and do not provide the same richness of information as cameras. Vision-based systems are also more attractive because they are inexpensive and lightweight.

Limbed climbing robots are designed to explore challenging vertical walls, such as the skylights of the Moon and Mars. In such robots, the primary role of a hand-eye camera is to accurately estimate 3D positions of graspable points (i.e., convex terrain surfaces) thanks to its close-up views. While conventional climbing robots often employ RGB-D cameras as hand-eye cameras to facilitate straightforward 3D terrain mapping and graspable point detection, RGB-D cameras are large and consume considerable power. This work presents a 3D terrain mapping system designed for space exploration using limbed climbing robots equipped with a monocular hand-eye camera. Compared to RGB-D cameras, monocular cameras are more lightweight, compact structures, and have lower power consumption. Although monocular SLAM can be used to construct 3D maps, it suffers from scale ambiguity. To address this limitation, we propose a SLAM method that fuses monocular visual constraints with limb forward kinematics. The proposed method jointly estimates time-series gripper poses and the global metric scale of the 3D map based on factor graph optimization. We validate the proposed framework through both physics-based simulations and real-world experiments. The results demonstrate that our framework constructs a metrically scaled 3D terrain map in real-time and enables autonomous grasping of convex terrain surfaces using a monocular hand-eye camera, without relying on RGB-D cameras. Our method contributes to scalable and energy-efficient perception for future space missions involving limbed climbing robots. See the video summary here: https://youtu.be/fMBrrVNKJfc

This paper explores a physical human-robot collaboration (pHRC) task involving the joint insertion of a board into a frame by a sightless robot and a human operator. While admittance control is commonly used in pHRC tasks, it can be challenging to measure the force/torque applied by the human for accurate human intent estimation, limiting the robot's ability to assist in the collaborative task. Other methods that attempt to solve pHRC tasks using reinforcement learning (RL) are also unsuitable for the board-insertion task due to its safety constraints and sparse rewards. Therefore, we propose a novel RL approach that utilizes a human-designed admittance controller to facilitate more active robot behavior and reduce human effort. Through simulation and real-world experiments, we demonstrate that our approach outperforms admittance control in terms of success rate and task completion time. Additionally, we observed a significant reduction in measured force/torque when using our proposed approach compared to admittance control. The video of the experiments is available at https://youtu.be/va07Gw6YIog.

Auto-bidding serves as a critical tool for advertisers to improve their advertising performance. Recent progress has demonstrated that AI-Generated Bidding (AIGB), which learns a conditional generative planner from offline data, achieves superior performance compared to typical offline reinforcement learning (RL)-based auto-bidding methods. However, existing AIGB methods still face a performance bottleneck due to their inherent inability to explore beyond the static offline dataset. To address this, we propose {AIGB-Pearl} (\emph{{P}lanning with {E}valu{A}tor via RL}), a novel method that integrates generative planning and policy optimization. The core of AIGB-Pearl lies in constructing a trajectory evaluator for scoring generation quality and designing a provably sound KL-Lipschitz-constrained score maximization scheme to ensure safe and efficient exploration beyond the offline dataset. A practical algorithm incorporating the synchronous coupling technique is further devised to ensure the model regularity required by the proposed scheme. Extensive experiments on both simulated and real-world advertising systems demonstrate the state-of-the-art performance of our approach.

Robots in real-world environments are often required to move/manipulate objects comparable in weight to their own bodies. Compared to grasping and carrying, pushing provides a more straightforward and efficient non-prehensile manipulation strategy, avoiding complex grasp design while leveraging direct contact to regulate an object's pose. Achieving effective pushing, however, demands both sufficient manipulation forces and the ability to maintain stability, which is particularly challenging when dealing with heavy or irregular objects. To address these challenges, we propose HeLoM, a learning-based hierarchical whole-body manipulation framework for a hexapod robot that exploits coordinated multi-limb control. Inspired by the cooperative strategies of multi-legged insects, our framework leverages redundant contact points and high degrees of freedom to enable dynamic redistribution of contact forces. HeLoM's high-level planner plans pushing behaviors and target object poses, while its low-level controller maintains locomotion stability and generates dynamically consistent joint actions. Our policies trained in simulation are directly deployed on real robots without additional fine-tuning. This design allows the robot to maintain balance while exerting continuous and controllable pushing forces through coordinated foreleg interaction and supportive hind-leg propulsion. We validate the effectiveness of HeLoM through both simulation and real-world experiments. Results show that our framework can stably push boxes of varying sizes and unknown physical properties to designated goal poses in the real world.

Universal grasping with multi-fingered dexterous hands is a fundamental challenge in robotic manipulation. While recent approaches successfully learn closed-loop grasping policies using reinforcement learning (RL), the inherent difficulty of high-dimensional, long-horizon exploration necessitates complex reward and curriculum design, often resulting in suboptimal solutions across diverse objects. We propose DemoGrasp, a simple yet effective method for learning universal dexterous grasping. We start from a single successful demonstration trajectory of grasping a specific object and adapt to novel objects and poses by editing the robot actions in this trajectory: changing the wrist pose determines where to grasp, and changing the hand joint angles determines how to grasp. We formulate this trajectory editing as a single-step Markov Decision Process (MDP) and use RL to optimize a universal policy across hundreds of objects in parallel in simulation, with a simple reward consisting of a binary success term and a robot-table collision penalty. In simulation, DemoGrasp achieves a 95% success rate on DexGraspNet objects using the Shadow Hand, outperforming previous state-of-the-art methods. It also shows strong transferability, achieving an average success rate of 84.6% across diverse dexterous hand embodiments on six unseen object datasets, while being trained on only 175 objects. Through vision-based imitation learning, our policy successfully grasps 110 unseen real-world objects, including small, thin items. It generalizes to spatial, background, and lighting changes, supports both RGB and depth inputs, and extends to language-guided grasping in cluttered scenes.