30 June 2022 in IEEE Robotics and Automation Letters
We address a challenging multi-agent pathfinding (MAPF) problem for hundreds of agents moving on a 2D roadmap with continuous time. Despite its known potential for producing better solutions compared to typical grid and discrete-time cases, few approaches have been established to solve this problem due to the intractability of collision checks on a large scale. In this work, we propose Prioritized Safe-Interval Path Planning with Continuous-Time Conflicts (PSIPP/CTC) that extends a scalable prioritized planning algorithm to work on the 2D roadmap and continuous-time setup by alleviating intensive collision checks. Our approach involves a novel concept named Continuous-Time Conflict (CTC), which describes a pair among vertices and edges associated with continuous-time intervals within which collisions can happen between agents. We pre-compute CTCs using geometric neighbor-search and sweeping techniques and annotate roadmaps with the CTCs just once before planning starts. Doing so allows us to efficiently enumerate collision-free time intervals for all vertices and edges and find each agent's path with continuous time in prioritized planning. Extensive experimental evaluations demonstrate that PSIPP/CTC significantly outperforms existing methods in terms of planning success rate and runtime while maintaining an acceptable solution quality. As a proof of concept, we also confirmed the effectiveness of the proposed approach on a physics simulation with differential wheeled robots.
8 June 2023 in IEEE Robotics and Automation Letters
This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms. In action-constrained RL, each action taken by the learning system must comply with certain constraints. These constraints are crucial for ensuring the feasibility and safety of actions in real-world systems. We evaluate existing algorithms and their novel variants across multiple robotics control environments, encompassing multiple action constraint types. Our evaluation provides the first in-depth perspective of the field, revealing surprising insights, including the effectiveness of a straightforward baseline approach. The benchmark problems and associated code utilized in our experiments are made available online at github.com/omron-sinicx/action-constrained-RL-benchmark for further research and development.
8 December 2020 in IEEE Robotics and Automation Letters
Forecasting human activities observed in videos is a long-standing challenge in computer vision and robotics and is also beneficial for various real-world applications such as mobile robot navigation and drone landing. In this work, we present a new forecasting task called crowd density forecasting. Given a video of a crowd captured by a surveillance camera, our goal is to predict how the density of the crowd will change in unseen future frames. To address this task, we have developed the patch-based density forecasting networks (PDFNs), which directly forecasts crowd density maps of future frames instead of trajectories of each moving person in the crowd. The proposed PDFNs represent crowd density maps based on spatially or spatiotemporally overlapping patches and learn a simple density dynamics of fewer people in each patch. Doing so allows us to efficiently deal with diverse and complex crowd density dynamics observed when input videos involve a variable number of crowds moving independently. Experimental results with several public datasets of surveillance videos demonstrate the effectiveness of our approaches compared with state-of-the-art forecasting methods.
16 June 2023 in IEEE Access
This paper examines an importance rank learning method of objects in urban scenes for assisting visually impaired people. Object detection methods have been used to assist visually impaired people in identifying obstacles in urban scenes, such as cars and trees. However, these existing methods are not dedicated to predicting which obstacle is important. Thus, we propose a method that estimates the importance of objects and warns them to users in order of importance ranking. We introduce a neural network-based ranking estimation method to predict the importance ranking of objects. In particular, our method uses optical flow from the previous frame and region data of detected objects as input. It helps to consider states of moving objects ( e.g ., cars, motorbikes, people) in a scene. Experimental results show that our model outperforms three other baselines qualitatively and quantitatively. Furthermore, our method was highly evaluated than the baseline methods by qualified caregivers of the visually impaired people.