Aligning robot navigation with human preferences is essential for ensuring comfortable and predictable robot movement in shared spaces, facilitating seamless human-robot coexistence. While preference-based learning methods, such as reinforcement learning from human feedback (RLHF), enable this alignment, the choice of the preference collection interface may influence the process. Traditional 2D interfaces provide structured views but lack spatial depth, whereas immersive VR offers richer perception, potentially affecting preference articulation. This study systematically examines how the interface modality impacts human preference collection and navigation policy alignment. We introduce a novel dataset of 2,325 human preference queries collected through both VR and 2D interfaces, revealing significant differences in user experience, preference consistency, and policy outcomes. Our findings highlight the trade-offs between immersion, perception, and preference reliability, emphasizing the importance of interface selection in preference-based robot learning. The dataset will be publicly released to support future research.

For scene understanding in unstructured environments, an accurate and uncertainty-aware metric-semantic mapping is required to enable informed action selection by autonomous systems. Existing mapping methods often suffer from overconfident semantic predictions, and sparse and noisy depth sensing, leading to inconsistent map representations. In this paper, we therefore introduce EvidMTL, a multi-task learning framework that uses evidential heads for depth estimation and semantic segmentation, enabling uncertainty-aware inference from monocular RGB images. To enable uncertainty-calibrated evidential multi-task learning, we propose a novel evidential depth loss function that jointly optimizes the belief strength of the depth prediction in conjunction with evidential segmentation loss. Building on this, we present EvidKimera, an uncertainty-aware semantic surface mapping framework, which uses evidential depth and semantics prediction for improved 3D metric-semantic consistency. We train and evaluate EvidMTL on the NYUDepthV2 and assess its zero-shot performance on ScanNetV2, demonstrating superior uncertainty estimation compared to conventional approaches while maintaining comparable depth estimation and semantic segmentation. In zero-shot mapping tests on ScanNetV2, EvidKimera outperforms Kimera in semantic surface mapping accuracy and consistency, highlighting the benefits of uncertainty-aware mapping and underscoring its potential for real-world robotic applications.

Robust and accurate proprioceptive state estimation of the main body is crucial for legged robots to execute tasks in extreme environments where exteroceptive sensors, such as LiDARs and cameras may become unreliable. In this paper, we propose DogLegs, a state estimation system for legged robots that fuses the measurements from a body-mounted inertial measurement unit (Body-IMU), joint encoders, and multiple leg-mounted IMUs (Leg-IMU) using an extended Kalman filter (EKF). The filter system contains the error states of all IMU frames. The Leg-IMUs are used to detect foot contact, thereby providing zero velocity measurements to update the state of the Leg-IMU frames. Additionally, we compute the relative position constraints between the Body-IMU and Leg-IMUs by the leg kinematics and use them to update the main body state and reduce the error drift of the individual IMU frames. Field experimental results have shown that our proposed system can achieve better state estimation accuracy compared to the traditional leg odometry method (using only Body-IMU and joint encoders) across different terrains. We make our datasets publicly available to benefit the research community.

Automating labor-intensive tasks such as crop monitoring with robots is essential for enhancing production and conserving resources. However, autonomously monitoring horticulture crops remains challenging due to their complex structures, which often result in fruit occlusions. Existing view planning methods attempt to reduce occlusions but either struggle to achieve adequate coverage or incur high robot motion costs. We introduce a global optimization approach for view motion planning that aims to minimize robot motion costs while maximizing fruit coverage. To this end, we leverage coverage constraints derived from the set covering problem (SCP) within a shortest Hamiltonian path problem (SHPP) formulation. While both SCP and SHPP are well-established, their tailored integration enables a unified framework that computes a global view path with minimized motion while ensuring full coverage of selected targets. Given the NP-hard nature of the problem, we employ a region-prior-based selection of coverage targets and a sparse graph structure to achieve effective optimization outcomes within a limited time. Experiments in simulation demonstrate that our method detects more fruits, enhances surface coverage, and achieves higher volume accuracy than the motion-efficient baseline with a moderate increase in motion cost, while significantly reducing motion costs compared to the coverage-focused baseline. Real-world experiments further confirm the practical applicability of our approach.

The increasing use of robots in human-centric public spaces such as shopping malls, sidewalks, and hospitals, requires understanding of how pedestrians respond to their presence. However, existing research lacks comprehensive datasets that capture the full range of pedestrian behaviors, e.g., including avoidance, neutrality, and attraction in the presence of robots. Such datasets can be used to effectively learn models capable of accurately predicting diverse responses of pedestrians to robot presence, which are crucial for advancing robot navigation strategies and optimizing pedestrian-aware motion planning. In this paper, we address these challenges by collecting a novel dataset of pedestrian motion in two outdoor locations under three distinct conditions, i.e., no robot presence, a stationary robot, and a moving robot. Thus, unlike existing datasets, ours explicitly encapsulates variations in pedestrian behavior across the different robot conditions. Using our dataset, we propose a novel Neural Social Robot Force Model (NSRFM), an extension of the traditional Social Force Model that integrates neural networks and robot-induced forces to better predict pedestrian behavior in the presence of robots. We validate the NSRFM by comparing its generated trajectories on different real-world datasets. Furthermore, we implemented it in simulation to enable the learning and benchmarking of robot navigation strategies based on their impact on pedestrian movement. Our results demonstrate the model's effectiveness in replicating real-world pedestrian reactions and its its utility in developing, evaluating, and benchmarking social robot navigation algorithms.

Searching for objects in cluttered environments requires selecting efficient viewpoints and manipulation actions to remove occlusions and reduce uncertainty in object locations, shapes, and categories. In this work, we address the problem of manipulation-enhanced semantic mapping, where a robot has to efficiently identify all objects in a cluttered shelf. Although Partially Observable Markov Decision Processes~(POMDPs) are standard for decision-making under uncertainty, representing unstructured interactive worlds remains challenging in this formalism. To tackle this, we define a POMDP whose belief is summarized by a metric-semantic grid map and propose a novel framework that uses neural networks to perform map-space belief updates to reason efficiently and simultaneously about object geometries, locations, categories, occlusions, and manipulation physics. Further, to enable accurate information gain analysis, the learned belief updates should maintain calibrated estimates of uncertainty. Therefore, we propose Calibrated Neural-Accelerated Belief Updates (CNABUs) to learn a belief propagation model that generalizes to novel scenarios and provides confidence-calibrated predictions for unknown areas. Our experiments show that our novel POMDP planner improves map completeness and accuracy over existing methods in challenging simulations and successfully transfers to real-world cluttered shelves in zero-shot fashion.

Reinforcement learning (RL) has been successfully applied to a variety of robotics applications, where it outperforms classical methods. However, the safety aspect of RL and the transfer to the real world remain an open challenge. A prominent field for tackling this challenge and ensuring the safety of the agents during training and execution is safe reinforcement learning. Safe RL can be achieved through constrained RL and safe exploration approaches. The former learns the safety constraints over the course of training to achieve a safe behavior by the end of training, at the cost of high number of collisions at earlier stages of the training. The latter offers robust safety by enforcing the safety constraints as hard constraints, which prevents collisions but hinders the exploration of the RL agent, resulting in lower rewards and poor performance. To overcome those drawbacks, we propose a novel safety shield, that combines the robustness of the optimization-based controllers with the long prediction capabilities of the RL agents, allowing the RL agent to adaptively tune the parameters of the controller. Our approach is able to improve the exploration of the RL agents for navigation tasks, while minimizing the number of collisions. Experiments in simulation show that our approach outperforms state-of-the-art baselines in the reached goals-to-collisions ratio in different challenging environments. The goals-to-collisions ratio metrics emphasizes the importance of minimizing the number of collisions, while learning to accomplish the task. Our approach achieves a higher number of reached goals compared to the classic safety shields and fewer collisions compared to constrained RL approaches. Finally, we demonstrate the performance of the proposed method in a real-world experiment.

Fruit monitoring plays an important role in crop management, and rising global fruit consumption combined with labor shortages necessitates automated monitoring with robots. However, occlusions from plant foliage often hinder accurate shape and pose estimation. Therefore, we propose an active fruit shape and pose estimation method that physically manipulates occluding leaves to reveal hidden fruits. This paper introduces a framework that plans robot actions to maximize visibility and minimize leaf damage. We developed a novel scene-consistent shape completion technique to improve fruit estimation under heavy occlusion and utilize a perception-driven deformation graph model to predict leaf deformation during planning. Experiments on artificial and real sweet pepper plants demonstrate that our method enables robots to safely move leaves aside, exposing fruits for accurate shape and pose estimation, outperforming baseline methods. Project page: https://shaoxiongyao.github.io/lmap-ssc/.

Peg-in-hole assembly in unknown environments is a challenging task due to onboard sensor errors, which result in uncertainty and variations in task parameters such as the hole position and orientation. Meta Reinforcement Learning (Meta RL) has been proposed to mitigate this problem as it learns how to quickly adapt to new tasks with different parameters. However, previous approaches either depend on a sample-inefficient procedure or human demonstrations to perform the task in the real world. Our work modifies the data used by the Meta RL agent and uses simple features that can be easily measured in the real world even with an uncalibrated camera. We further adapt the Meta RL agent to use data from a force/torque sensor, instead of the camera, to perform the assembly, using a small amount of training data. Finally, we propose a fine-tuning method that consistently and safely adapts to out-of-distribution tasks with parameters that differ by a factor of 10 from the training tasks. Our results demonstrate that the proposed data modification significantly enhances the training and adaptation efficiency and enables the agent to achieve 100% success in tasks with different hole positions and orientations. Experiments on a real robot confirm that both camera- and force/torque sensor-equipped agents achieve 100% success in tasks with unknown hole positions, matching their simulation performance and validating the approach's robustness and applicability. Compared to the previous work with sample-inefficient adaptation, our proposed methods are 10 times more sample-efficient in the real-world tasks.

The presence of robots amongst pedestrians affects them causing deviation to their trajectories. Existing methods suffer from the limitation of not being able to objectively measure this deviation in unseen cases. In order to solve this issue, we introduce a simulation framework that repetitively measures and benchmarks the deviation in trajectory of pedestrians due to robots driven by different navigation algorithms. We simulate the deviation behavior of the pedestrians using an enhanced Social Force Model (SFM) with a robot force component that accounts for the influence of robots on pedestrian behavior, resulting in the Social Robot Force Model (SRFM). Parameters for this model are learned using the pedestrian trajectories from the JRDB dataset [1]. Pedestrians are then simulated using the SRFM with and without the robot force component to objectively measure the deviation to their trajectory caused by the robot in 5 different scenarios. Our work in this paper is a proof of concept that shows objectively measuring the pedestrian reaction to robot is possible. We use our simulation to train two different RL policies and evaluate them against traditional navigation models.