Socially CompliAnt Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation

Karnan, Haresh; Nair, Anirudh; Xiao, Xuesu; Warnell, Garrett; Pirk, Sören; Toshev, Alexander; Hart, Justin W.; Biswas, Joydeep; Stone, Peter

doi:10.1109/lra.2022.3184025

Cited by 43 publications

(10 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They evaluated different Markov Decision Process models and compared them with the baseline implementation of a global path planner and local trajectory planner without social costs. More recently, Karnan et al [337] collected a largescale dataset of socially compliant navigation demonstrations. They used it to perform behavior cloning [338] for a global path planner and local trajectory planner agents that aimed to mimic human navigation behaviors.…”

Section: Inverse Reinforcement Learningmentioning

confidence: 99%

Bridging Requirements, Planning, and Evaluation: A Review of Social Robot Navigation

Karwowski,

Szynkiewicz,

Niewiadomska-Szynkiewicz

2024

Sensors

View full text Add to dashboard Cite

Navigation lies at the core of social robotics, enabling robots to navigate and interact seamlessly in human environments. The primary focus of human-aware robot navigation is minimizing discomfort among surrounding humans. Our review explores user studies, examining factors that cause human discomfort, to perform the grounding of social robot navigation requirements and to form a taxonomy of elementary necessities that should be implemented by comprehensive algorithms. This survey also discusses human-aware navigation from an algorithmic perspective, reviewing the perception and motion planning methods integral to social navigation. Additionally, the review investigates different types of studies and tools facilitating the evaluation of social robot navigation approaches, namely datasets, simulators, and benchmarks. Our survey also identifies the main challenges of human-aware navigation, highlighting the essential future work perspectives. This work stands out from other review papers, as it not only investigates the variety of methods for implementing human awareness in robot control systems but also classifies the approaches according to the grounded requirements regarded in their objectives.

show abstract

Section: Inverse Reinforcement Learningmentioning

confidence: 99%

Bridging Requirements, Planning, and Evaluation: A Review of Social Robot Navigation

Karwowski,

Szynkiewicz,

Niewiadomska-Szynkiewicz

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…5. Different from social navigation datasets JRDB [19] and SCAND [40] where they mainly operate the robot in a crowded environment and imitate human behavior to avoid obstacles, we intend to operate the robot near the static obstacles while navigating to include more samples of obstacles at close distances.…”

Section: B Octree Decodermentioning

confidence: 99%

StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks

Li¹,

Li²,

Akmandor³

et al. 2022

Preprint

View full text Add to dashboard Cite

Obstacle detection is a safety-critical problem in robot navigation, where stereo matching is a popular visionbased approach. While deep neural networks have shown impressive results in computer vision, most of the previous obstacle detection works only leverage traditional stereo matching techniques to meet the computational constraints for real-time feedback. This paper proposes a computationally efficient method that leverages a deep neural network to detect occupancy from stereo images directly. Instead of learning the point cloud correspondence from the stereo data, our approach extracts the compact obstacle distribution based on volumetric representations. In addition, we prune the computation of safety irrelevant spaces in a coarse-to-fine manner based on octrees generated by the decoder. As a result, we achieve real-time performance on the onboard computer (NVIDIA Jetson TX2). Our approach detects obstacles accurately in the range of 32 meters and achieves better IoU (Intersection over Union) and CD (Chamfer Distance) scores with only 2% of the computation cost of the state-of-the-art stereo model. Furthermore, we validate our method's robustness and real-world feasibility through autonomous navigation experiments with a real robot. Hence, our work contributes toward closing the gap between the stereo-based system in robot perception and state-of-theart stereo models in computer vision. To counter the scarcity of high-quality real-world indoor stereo datasets, we collect a 1.36 hours stereo dataset with a Jackal robot which is used to finetune our model. The dataset, the code, and more visualizations are available at https://lhy.xyz/stereovoxelnet/.

show abstract

“…Adjusting or learning the navigation behavior of a robot based on feedback or demonstration has been the focus of various studies [6], [7]. Especially, deep learning-based approaches shine by their ability to learn from subtle and implicit features in their environment [8], [9], [10]. This is a perfect prerequisite to use a deep reinforcement learning architecture for our personalized navigation controller.…”

Section: Related Workmentioning

confidence: 99%

Learning Depth Vision-Based Personalized Robot Navigation From Dynamic Demonstrations in Virtual Reality

Jorge¹,

Corral²,

Kreis³

et al. 2022

Preprint

View full text Add to dashboard Cite

For the best human-robot interaction experience, the robot's navigation policy should take into account personal preferences of the user. In this paper, we present a learning framework complemented by a perception pipeline to train a depth vision-based, personalized navigation controller from user demonstrations. Our refined virtual reality interface enables the demonstration of robot navigation trajectories under motion of the user for dynamic interaction scenarios. In a detailed analysis, we evaluate different configurations of the perception pipeline. As the experiments demonstrate, our new pipeline compresses the perceived depth images to a latent state representation and, thus, enables efficient reasoning about the robot's dynamic environment to the learning. We discuss the robot's navigation performance in various virtual scenes by enrolling a variational autoencoder in combination with a motion predictor and demonstrate the first personalized robot navigation controller that solely relies on depth images.

show abstract

Socially CompliAnt Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation

Cited by 43 publications

References 37 publications

Bridging Requirements, Planning, and Evaluation: A Review of Social Robot Navigation

Bridging Requirements, Planning, and Evaluation: A Review of Social Robot Navigation

StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks

Learning Depth Vision-Based Personalized Robot Navigation From Dynamic Demonstrations in Virtual Reality

Contact Info

Product

Resources

About