Fei Xia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Fei Xia has a total of 134 co-authors. Here are the top co-authors by number of shared publications:
Silvio Savarese
5 shared publications- Roberto Martín-Martín
University of Texas at Austin, Austin, TX, USA
4 shared publications - David Tse
Stanford University
3 shared publications - James Zou
Department of Biomedical Data Science, Stanford University, Stanford, USA
3 shared publications - Alexander Toshev
Robotics at Google
2 shared publications - Amir Sadeghian
Computer Science, Stanford University, Menlo Park, CA United States of America 94025
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 20 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Human-Robot Interaction
- Vol. 14 (2) , 1-65
Principles and Guidelines for Evaluating Social Robot Navigation Algorithms
A major challenge to deploying robots widely is navigation in human-populated environments, commonly referred to as social robot navigation . While the field of social navigation has advanced tremendously in recent years, the fair evaluation of algorithms that tackle social navigation remains hard because it involves not just robotic agents moving in static environments but also dynamic human agents and their perceptions of the appropriateness of robot behavior. In contrast, clear, repeatable, and accessible benchmarks have accelerated progress in fields like computer vision, natural language processing and traditional robot navigation by enabling researchers to fairly compare algorithms, revealing limitations of existing solutions and illuminating promising new directions. We believe the same approach can benefit social navigation. In this article, we pave the road toward common, widely accessible, and repeatable benchmarking criteria to evaluate social robot navigation. Our contributions include (a) a definition of a socially navigating robot as one that respects the principles of safety, comfort, legibility, politeness, social competency, agent understanding, proactivity, and responsiveness to context, (b) guidelines for the use of metrics, development of scenarios, benchmarks, datasets, and simulators to evaluate social navigation, and (c) a design of a social navigation metrics framework to make it easier to compare results from different simulators, robots, and datasets.
- 20 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Human-Robot Interaction
- Vol. 14 (2) , 1-65
Top Cited PapersOpen AccessPrinciples and Guidelines for Evaluating Social Robot Navigation Algorithms
A major challenge to deploying robots widely is navigation in human-populated environments, commonly referred to as social robot navigation . While the field of social navigation has advanced tremendously in recent years, the fair evaluation of algorithms that tackle social navigation remains hard because it involves not just robotic agents moving in static environments but also dynamic human agents and their perceptions of the appropriateness of robot behavior. In contrast, clear, repeatable, and accessible benchmarks have accelerated progress in fields like computer vision, natural language processing and traditional robot navigation by enabling researchers to fairly compare algorithms, revealing limitations of existing solutions and illuminating promising new directions. We believe the same approach can benefit social navigation. In this article, we pave the road toward common, widely accessible, and repeatable benchmarking criteria to evaluate social robot navigation. Our contributions include (a) a definition of a socially navigating robot as one that respects the principles of safety, comfort, legibility, politeness, social competency, agent understanding, proactivity, and responsiveness to context, (b) guidelines for the use of metrics, development of scenarios, benchmarks, datasets, and simulators to evaluate social navigation, and (c) a design of a social navigation metrics framework to make it easier to compare results from different simulators, robots, and datasets.
- Open Access
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 482-491
Generative Expressive Robot Behaviors using Large Language Models
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 482-491
Open AccessGenerative Expressive Robot Behaviors using Large Language Models
- 18 January 2023
- Published by Wiley in European Journal of Inorganic Chemistry
- Vol. 26 (9)
Alcohol‐Assisted Synthesis of Sheet‐Like ZSM‐5 Zeolites with Controllable Aspect Ratios
Sheet‐like ZSM‐5 has been regarded as a promising material for catalytic applications due to its diffusion superiority. However, it still remains a challenge to obtain a desirable sheet‐like morphology because of the complex synthesis process of zeolites. Here, a facile strategy for synthesizing sheet‐like ZSM‐5 is developed by only adding ethanol as zeolite growth modifier in the synthesis gel. It is thought that ethanol might be preferentially absorbed on the {010} surface of zeolite crystals, interact with the exposed silicon hydroxyl groups on the crystal {010} facet, and suppress the growth of b axis, resulting in the sheet‐like shape. Through finely tunning synthesis parameters, sheet‐like ZSM‐5 crystals with thin b‐axis thickness of 90 nm and different aspect ratios could be obtained. Owing to its shorter diffusion path and optimized acidity, sheet‐like ZSM‐5 exhibits better catalytic performance than conventional ZSM‐5 in the alkylation of benzene with ethanol.
- 18 January 2023
- Published by Wiley in European Journal of Inorganic Chemistry
- Vol. 26 (9)
Alcohol‐Assisted Synthesis of Sheet‐Like ZSM‐5 Zeolites with Controllable Aspect Ratios
Sheet‐like ZSM‐5 has been regarded as a promising material for catalytic applications due to its diffusion superiority. However, it still remains a challenge to obtain a desirable sheet‐like morphology because of the complex synthesis process of zeolites. Here, a facile strategy for synthesizing sheet‐like ZSM‐5 is developed by only adding ethanol as zeolite growth modifier in the synthesis gel. It is thought that ethanol might be preferentially absorbed on the {010} surface of zeolite crystals, interact with the exposed silicon hydroxyl groups on the crystal {010} facet, and suppress the growth of b axis, resulting in the sheet‐like shape. Through finely tunning synthesis parameters, sheet‐like ZSM‐5 crystals with thin b‐axis thickness of 90 nm and different aspect ratios could be obtained. Owing to its shorter diffusion path and optimized acidity, sheet‐like ZSM‐5 exhibits better catalytic performance than conventional ZSM‐5 in the alkylation of benzene with ethanol.
- Open Access
Open-vocabulary Queryable Scene Representations for Real World Planning
Large language models (LLMs) have unlocked new capabilities of task planning from human instructions. However, prior attempts to apply LLMs to real-world robotic tasks are limited by the lack of grounding in the surrounding scene. In this paper, we develop NLMap, an open-vocabulary and queryable scene representation to address this problem. NLMap serves as a framework to gather and integrate contextual information into LLM planners, allowing them to see and query available objects in the scene before generating a context-conditioned plan. NLMap first establishes a natural language queryable scene representation with Visual Language models (VLMs). An LLM based object proposal module parses instructions and proposes involved objects to query the scene representation for object availability and location. An LLM planner then plans with such information about the scene. NLMap allows robots to operate without a fixed list of objects nor executable options, enabling real robot operation unachievable by previous methods. Project website: https://nlmap-saycan.github.io
Open AccessOpen-vocabulary Queryable Scene Representations for Real World Planning
Large language models (LLMs) have unlocked new capabilities of task planning from human instructions. However, prior attempts to apply LLMs to real-world robotic tasks are limited by the lack of grounding in the surrounding scene. In this paper, we develop NLMap, an open-vocabulary and queryable scene representation to address this problem. NLMap serves as a framework to gather and integrate contextual information into LLM planners, allowing them to see and query available objects in the scene before generating a context-conditioned plan. NLMap first establishes a natural language queryable scene representation with Visual Language models (VLMs). An LLM based object proposal module parses instructions and proposes involved objects to query the scene representation for object availability and location. An LLM planner then plans with such information about the scene. NLMap allows robots to operate without a fixed list of objects nor executable options, enabling real robot operation unachievable by previous methods. Project website: https://nlmap-saycan.github.io
- Open Access
SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds
3D object detection in point clouds is a core component for modern robotics and autonomous driving systems. A key challenge in 3D object detection comes from the inherent sparse nature of point occupancy within the 3D scene. In this paper, we propose Sparse Window Transformer (SWFormer ), a scalable and accurate model for 3D object detection, which can take full advantage of the sparsity of point clouds. Built upon the idea of window-based Transformers, SWFormer converts 3D points into sparse voxels and windows, and then processes these variable-length sparse windows efficiently using a bucketing scheme. In addition to self-attention within each spatial window, our SWFormer also captures cross-window correlation with multi-scale feature fusion and window shifting operations. To further address the unique challenge of detecting 3D objects accurately from sparse features, we propose a new voxel diffusion technique. Experimental results on the Waymo Open Dataset show our SWFormer achieves state-of-the-art 73.36 L2 mAPH on vehicle and pedestrian for 3D object detection on the official test set, outperforming all previous single-stage and two-stage models, while being much more efficient.
Open AccessSWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds
3D object detection in point clouds is a core component for modern robotics and autonomous driving systems. A key challenge in 3D object detection comes from the inherent sparse nature of point occupancy within the 3D scene. In this paper, we propose Sparse Window Transformer (SWFormer ), a scalable and accurate model for 3D object detection, which can take full advantage of the sparsity of point clouds. Built upon the idea of window-based Transformers, SWFormer converts 3D points into sparse voxels and windows, and then processes these variable-length sparse windows efficiently using a bucketing scheme. In addition to self-attention within each spatial window, our SWFormer also captures cross-window correlation with multi-scale feature fusion and window shifting operations. To further address the unique challenge of detecting 3D objects accurately from sparse features, we propose a new voxel diffusion technique. Experimental results on the Waymo Open Dataset show our SWFormer achieves state-of-the-art 73.36 L2 mAPH on vehicle and pedestrian for 3D object detection on the official test set, outperforming all previous single-stage and two-stage models, while being much more efficient.
- 4 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, 47-50
Research on Path Planning of Substation Robot Inspection Based on Cloud Computing
With the continuous development of smart grids, the number of substations has also increased. Aiming at the problems of heavy inspection tasks in substations and low level of manual inspection visualization, this paper proposes a cloud computing-based substation robot inspection path planning method. Through the equivalent modeling of the substation scene based on image recognition, the motion model of the inspection robot is constructed, and the inspection path of the substation robot is planned by the improved deep reinforcement learning algorithm. Through the actual substation equivalent verification, the proposed deep reinforcement learning algorithm of the improved convolutional neural network has shorter calculation time and higher efficiency than the traditional algorithm. It is more conducive to accurate planning of the inspection path of the substation inspection robot, and improves the substation inspection. The level of automation.
- 4 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, 47-50
Research on Path Planning of Substation Robot Inspection Based on Cloud Computing
With the continuous development of smart grids, the number of substations has also increased. Aiming at the problems of heavy inspection tasks in substations and low level of manual inspection visualization, this paper proposes a cloud computing-based substation robot inspection path planning method. Through the equivalent modeling of the substation scene based on image recognition, the motion model of the inspection robot is constructed, and the inspection path of the substation robot is planned by the improved deep reinforcement learning algorithm. Through the actual substation equivalent verification, the proposed deep reinforcement learning algorithm of the improved convolutional neural network has shorter calculation time and higher efficiency than the traditional algorithm. It is more conducive to accurate planning of the inspection path of the substation inspection robot, and improves the substation inspection. The level of automation.
- Open Access
Probabilistic Visual Navigation with Bidirectional Image Prediction
Humans can robustly follow a visual trajectory defined by a sequence of images (i.e. a video) regardless of substantial changes in the environment or the presence of obstacles. We aim at endowing similar visual navigation capabilities to mobile robots solely equipped with a RGB fisheye camera. We propose a novel probabilistic visual navigation system that learns to follow a sequence of images with bidirectional visual predictions conditioned on possible navigation velocities. By predicting bidirectionally (from start towards goal and vice versa) our method extends its predictive horizon enabling the robot to go around unseen large obstacles that are not visible in the video trajectory. Learning how to react to obstacles and potential risks in the visual field is achieved by imitating human teleoperators. Since the human teleoperation commands are diverse, we propose a probabilistic representation of trajectories that we can sample to find the safest path. Integrated into our navigation system, we present a novel localization approach that infers the current location of the robot based on the virtual predicted trajectories required to reach different images in the visual trajectory. We evaluate our navigation system quantitatively and qualitatively in multiple simulated and real environments and compare to state-of-the-art baselines.Our approach outperforms the most recent visual navigation methods with a large margin with regard to goal arrival rate, subgoal coverage rate, and success weighted by path length (SPL). Our method also generalizes to new robot embodiments never used during training.
Open AccessProbabilistic Visual Navigation with Bidirectional Image Prediction
Humans can robustly follow a visual trajectory defined by a sequence of images (i.e. a video) regardless of substantial changes in the environment or the presence of obstacles. We aim at endowing similar visual navigation capabilities to mobile robots solely equipped with a RGB fisheye camera. We propose a novel probabilistic visual navigation system that learns to follow a sequence of images with bidirectional visual predictions conditioned on possible navigation velocities. By predicting bidirectionally (from start towards goal and vice versa) our method extends its predictive horizon enabling the robot to go around unseen large obstacles that are not visible in the video trajectory. Learning how to react to obstacles and potential risks in the visual field is achieved by imitating human teleoperators. Since the human teleoperation commands are diverse, we propose a probabilistic representation of trajectories that we can sample to find the safest path. Integrated into our navigation system, we present a novel localization approach that infers the current location of the robot based on the virtual predicted trajectories required to reach different images in the visual trajectory. We evaluate our navigation system quantitatively and qualitatively in multiple simulated and real environments and compare to state-of-the-art baselines.Our approach outperforms the most recent visual navigation methods with a large margin with regard to goal arrival rate, subgoal coverage rate, and success weighted by path length (SPL). Our method also generalizes to new robot embodiments never used during training.
- Open Access
iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks
Recent research in embodied AI has been boosted by the use of simulation environments to develop and train robot learning approaches. However, the use of simulation has skewed the attention to tasks that only require what robotics simulators can simulate: motion and physical contact. We present iGibson 2.0, an open-source simulation environment that supports the simulation of a more diverse set of household tasks through three key innovations. First, iGibson 2.0 supports object states, including temperature, wetness level, cleanliness level, and toggled and sliced states, necessary to cover a wider range of tasks. Second, iGibson 2.0 implements a set of predicate logic functions that map the simulator states to logic states like Cooked or Soaked. Additionally, given a logic state, iGibson 2.0 can sample valid physical states that satisfy it. This functionality can generate potentially infinite instances of tasks with minimal effort from the users. The sampling mechanism allows our scenes to be more densely populated with small objects in semantically meaningful locations. Third, iGibson 2.0 includes a virtual reality (VR) interface to immerse humans in its scenes to collect demonstrations. As a result, we can collect demonstrations from humans on these new types of tasks, and use them for imitation learning. We evaluate the new capabilities of iGibson 2.0 to enable robot learning of novel tasks, in the hope of demonstrating the potential of this new simulator to support new research in embodied AI. iGibson 2.0 and its new dataset are publicly available at http://svl.stanford.edu/igibson/.
Open AccessiGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks
Recent research in embodied AI has been boosted by the use of simulation environments to develop and train robot learning approaches. However, the use of simulation has skewed the attention to tasks that only require what robotics simulators can simulate: motion and physical contact. We present iGibson 2.0, an open-source simulation environment that supports the simulation of a more diverse set of household tasks through three key innovations. First, iGibson 2.0 supports object states, including temperature, wetness level, cleanliness level, and toggled and sliced states, necessary to cover a wider range of tasks. Second, iGibson 2.0 implements a set of predicate logic functions that map the simulator states to logic states like Cooked or Soaked. Additionally, given a logic state, iGibson 2.0 can sample valid physical states that satisfy it. This functionality can generate potentially infinite instances of tasks with minimal effort from the users. The sampling mechanism allows our scenes to be more densely populated with small objects in semantically meaningful locations. Third, iGibson 2.0 includes a virtual reality (VR) interface to immerse humans in its scenes to collect demonstrations. As a result, we can collect demonstrations from humans on these new types of tasks, and use them for imitation learning. We evaluate the new capabilities of iGibson 2.0 to enable robot learning of novel tasks, in the hope of demonstrating the potential of this new simulator to support new research in embodied AI. iGibson 2.0 and its new dataset are publicly available at http://svl.stanford.edu/igibson/.
- Top Cited PapersOpen Access
- 25 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 37 (5) , 1328-1342
PoseRBPF: A Rao–Blackwellized Particle Filter for 6-D Object Pose Tracking
Tracking 6-D poses of objects from videos provides rich information to a robot in performing different tasks such as manipulation and navigation. In this article, we formulate the 6-D object pose tracking problem in the Rao–Blackwellized particle filtering framework, where the 3-D rotation and the 3-D translation of an object are decoupled. This factorization allows our approach, called PoseRBPF, to efficiently estimate the 3-D translation of an object along with the full distribution over the 3-D rotation. This is achieved by discretizing the rotation space in a fine-grained manner and training an autoencoder network to construct a codebook of feature embeddings for the discretized rotations. As a result, PoseRBPF can track objects with arbitrary symmetries while still maintaining adequate posterior distributions. Our approach achieves state-of-the-art results on two 6-D pose estimation benchmarks. We open-source our implementation at https://github.com/NVlabs/PoseRBPF.
- 25 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 37 (5) , 1328-1342
Top Cited PapersOpen AccessPoseRBPF: A Rao–Blackwellized Particle Filter for 6-D Object Pose Tracking
Tracking 6-D poses of objects from videos provides rich information to a robot in performing different tasks such as manipulation and navigation. In this article, we formulate the 6-D object pose tracking problem in the Rao–Blackwellized particle filtering framework, where the 3-D rotation and the 3-D translation of an object are decoupled. This factorization allows our approach, called PoseRBPF, to efficiently estimate the 3-D translation of an object along with the full distribution over the 3-D rotation. This is achieved by discretizing the rotation space in a fine-grained manner and training an autoencoder network to construct a codebook of feature embeddings for the discretized rotations. As a result, PoseRBPF can track objects with arbitrary symmetries while still maintaining adequate posterior distributions. Our approach achieves state-of-the-art results on two 6-D pose estimation benchmarks. We open-source our implementation at https://github.com/NVlabs/PoseRBPF.
- 30 January 2020
- Published by Wiley in Forest Pathology
- Vol. 50 (1)
Providencia rettgeri as the causal agent of the brown slime flux of Populus tomentosa
Brown slime flux seeps slowly out of wounds and flows down the bark of roadside Populus tomentosa in Beijing, China. Two bacterial isolates, SL2‐2 and SL3‐3, obtained from the brown slime flux were identified as Providencia rettgeri based on 16S rRNA gene sequencing. After inoculation into the bark of roadside P. tomentosa with sterile deionized water as a control, both SL2‐2 and SL3‐3 triggered the seepage of brown slime flux from the wounds; no slime flux arose from the control. In conclusion, P. rettgeri was the pathogenic bacterium causing brown slime flux on P. tomentosa probably by inhibiting wound healing. To our knowledge, this is the first report of P. rettgeri as a pathogen of plants.
- 30 January 2020
- Published by Wiley in Forest Pathology
- Vol. 50 (1)
Providencia rettgeri as the causal agent of the brown slime flux of Populus tomentosa
Brown slime flux seeps slowly out of wounds and flows down the bark of roadside Populus tomentosa in Beijing, China. Two bacterial isolates, SL2‐2 and SL3‐3, obtained from the brown slime flux were identified as Providencia rettgeri based on 16S rRNA gene sequencing. After inoculation into the bark of roadside P. tomentosa with sterile deionized water as a control, both SL2‐2 and SL3‐3 triggered the seepage of brown slime flux from the wounds; no slime flux arose from the control. In conclusion, P. rettgeri was the pathogenic bacterium causing brown slime flux on P. tomentosa probably by inhibiting wound healing. To our knowledge, this is the first report of P. rettgeri as a pathogen of plants.