Naoki Akai
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
Naoki Akai has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Takatsugu Hirayama
Nagoya University
5 shared publications - Hiroshi Murase
Nagoya University, Nagoya, Japan
3 shared publications - Koichi Ozaki
Graduate School of Engineering, Utsunomiya University, 7-1-2, Yoto, Utsunomiya 321-8585, Japan
3 shared publications Susumu Hara
3 shared publications- Yoichi Morales
Affiliation Intelligent Robotics and Communication Laboratories, Advanced Telecommunications Research Institute International, Soraku-gun, Kyoto, Japan
3 shared publications Hiroshi Murase
Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan
2 shared publications
Latest Publications
- 14 December 2025
- Published by Taylor & Francis in Advanced Robotics
- Vol. 40 (1) , 1-9
A LiDAR SLAM system for dense forest mapping with iterated motion distortion correction
- 14 December 2025
- Published by Taylor & Francis in Advanced Robotics
- Vol. 40 (1) , 1-9
A LiDAR SLAM system for dense forest mapping with iterated motion distortion correction
- Open Access
Spline-Interpolated Model Predictive Path Integral Control with Stein Variational Inference for Reactive Navigation
This paper presents a reactive navigation method that leverages a Model Predictive Path Integral (MPPI) control enhanced with spline interpolation for the control input sequence and Stein Variational Gradient Descent (SVGD). The MPPI framework addresses a nonlinear optimization problem by determining an optimal sequence of control inputs through a sampling-based approach. The efficacy of MPPI is significantly influenced by the sampling noise. To rapidly identify routes that circumvent large and/or newly detected obstacles, it is essential to employ high levels of sampling noise. However, such high noise levels result in jerky control input sequences, leading to non-smooth trajectories. To mitigate this issue, we propose the integration of spline interpolation within the MPPI process, enabling the generation of smooth control input sequences despite the utilization of substantial sampling noises. Nonetheless, the standard MPPI algorithm struggles in scenarios featuring multiple optimal or near-optimal solutions, such as environments with several viable obstacle avoidance paths, due to its assumption that the distribution over an optimal control input sequence can be closely approximated by a Gaussian distribution. To address this limitation, we extend our method by incorporating SVGD into the MPPI framework with spline interpolation. SVGD, rooted in the optimal transportation algorithm, possesses the unique ability to cluster samples around an optimal solution. Consequently, our approach facilitates robust reactive navigation by swiftly identifying obstacle avoidance paths while maintaining the smoothness of the control input sequences. The efficacy of our proposed method is validated on simulations with a quadrotor, demonstrating superior performance over existing baseline techniques.
Open AccessSpline-Interpolated Model Predictive Path Integral Control with Stein Variational Inference for Reactive Navigation
This paper presents a reactive navigation method that leverages a Model Predictive Path Integral (MPPI) control enhanced with spline interpolation for the control input sequence and Stein Variational Gradient Descent (SVGD). The MPPI framework addresses a nonlinear optimization problem by determining an optimal sequence of control inputs through a sampling-based approach. The efficacy of MPPI is significantly influenced by the sampling noise. To rapidly identify routes that circumvent large and/or newly detected obstacles, it is essential to employ high levels of sampling noise. However, such high noise levels result in jerky control input sequences, leading to non-smooth trajectories. To mitigate this issue, we propose the integration of spline interpolation within the MPPI process, enabling the generation of smooth control input sequences despite the utilization of substantial sampling noises. Nonetheless, the standard MPPI algorithm struggles in scenarios featuring multiple optimal or near-optimal solutions, such as environments with several viable obstacle avoidance paths, due to its assumption that the distribution over an optimal control input sequence can be closely approximated by a Gaussian distribution. To address this limitation, we extend our method by incorporating SVGD into the MPPI framework with spline interpolation. SVGD, rooted in the optimal transportation algorithm, possesses the unique ability to cluster samples around an optimal solution. Consequently, our approach facilitates robust reactive navigation by swiftly identifying obstacle avoidance paths while maintaining the smoothness of the control input sequences. The efficacy of our proposed method is validated on simulations with a quadrotor, demonstrating superior performance over existing baseline techniques.
- Open Access
Efficient Solution to 3D-LiDAR-based Monte Carlo Localization with Fusion of Measurement Model Optimization via Importance Sampling
This paper presents an efficient solution to 3D-LiDAR-based Monte Carlo localization (MCL). MCL robustly works if particles are exactly sampled around the ground truth. An inertial navigation system (INS) can be used for accurate sampling, but many particles are still needed to be used for solving the 3D localization problem even if INS is available. In particular, huge number of particles are necessary if INS is not available and it makes infeasible to perform 3D MCL in terms of the computational cost. Scan matching (SM), that is optimization-based localization, efficiently works even though INS is not available because SM can ignore movement constraints of a robot and/or device in its optimization process. However, SM sometimes determines an infeasible estimate against movement. We consider that MCL and SM have complemental advantages and disadvantages and propose a fusion method of MCL and SM. Because SM is considered as optimization of a measurement model in terms of the probabilistic modeling, we perform measurement model optimization as SM. The optimization result is then used to approximate the measurement model distribution and the approximated distribution is used to sample particles. The sampled particles are fused with MCL via importance sampling. As a result, the advantages of MCL and SM can be simultaneously utilized while mitigating their disadvantages. Experiments are conducted on the KITTI dataset and other two open datasets. Results show that the presented method can be run on a single CPU thread and accurately perform localization even if INS is not available.
Open AccessEfficient Solution to 3D-LiDAR-based Monte Carlo Localization with Fusion of Measurement Model Optimization via Importance Sampling
This paper presents an efficient solution to 3D-LiDAR-based Monte Carlo localization (MCL). MCL robustly works if particles are exactly sampled around the ground truth. An inertial navigation system (INS) can be used for accurate sampling, but many particles are still needed to be used for solving the 3D localization problem even if INS is available. In particular, huge number of particles are necessary if INS is not available and it makes infeasible to perform 3D MCL in terms of the computational cost. Scan matching (SM), that is optimization-based localization, efficiently works even though INS is not available because SM can ignore movement constraints of a robot and/or device in its optimization process. However, SM sometimes determines an infeasible estimate against movement. We consider that MCL and SM have complemental advantages and disadvantages and propose a fusion method of MCL and SM. Because SM is considered as optimization of a measurement model in terms of the probabilistic modeling, we perform measurement model optimization as SM. The optimization result is then used to approximate the measurement model distribution and the approximated distribution is used to sample particles. The sampled particles are fused with MCL via importance sampling. As a result, the advantages of MCL and SM can be simultaneously utilized while mitigating their disadvantages. Experiments are conducted on the KITTI dataset and other two open datasets. Results show that the presented method can be run on a single CPU thread and accurately perform localization even if INS is not available.
- 20 February 2023
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 18 (3) , 2221-2230
Experimental Study on Low-Speed Control for Motorcycles Using SPACAR Model and Gain-Scheduling Control
- 20 February 2023
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 18 (3) , 2221-2230
Experimental Study on Low-Speed Control for Motorcycles Using SPACAR Model and Gain-Scheduling Control
- 17 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Obstacle Avoidance with Zigzag Tentacles for Multirotor UAVs
In this paper, we present an extended tentacle-based obstacle avoidance method for multirotor unmanned aerial vehicles (UAVs). Our objective is to achieve a rapid and safe autonomous flight in narrow and complex spaces. Traditional tentacle-based obstacle avoidance methods generate only simple-shape candidate paths. Consequently, paths that bypass obstacles cannot be found and the moving speed of a UAV is needed to be decreased when navigating narrow spaces because the tentacles cannot be sufficiently extended. In the presented method, zigzag tentacles are generated. A UAV can fly through narrow spaces without decreasing its speed because the zigzag tentacles can find bypass paths. We conducted experiments with simulated and actual multirotor UAVs. The results show that the presented method achieved a rapid and safe autonomous flight in both experiments. In addition, we compare the presented method with the dynamic window approach which is a traditional tentacle-based method. This comparison shows the effectiveness of the zigzag tentacles, i.e., the presented method can achieve autonomous flight whereas the traditional method causes the UAV to become stuck.
- 17 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Obstacle Avoidance with Zigzag Tentacles for Multirotor UAVs
In this paper, we present an extended tentacle-based obstacle avoidance method for multirotor unmanned aerial vehicles (UAVs). Our objective is to achieve a rapid and safe autonomous flight in narrow and complex spaces. Traditional tentacle-based obstacle avoidance methods generate only simple-shape candidate paths. Consequently, paths that bypass obstacles cannot be found and the moving speed of a UAV is needed to be decreased when navigating narrow spaces because the tentacles cannot be sufficiently extended. In the presented method, zigzag tentacles are generated. A UAV can fly through narrow spaces without decreasing its speed because the zigzag tentacles can find bypass paths. We conducted experiments with simulated and actual multirotor UAVs. The results show that the presented method achieved a rapid and safe autonomous flight in both experiments. In addition, we compare the presented method with the dynamic window approach which is a traditional tentacle-based method. This comparison shows the effectiveness of the zigzag tentacles, i.e., the presented method can achieve autonomous flight whereas the traditional method causes the UAV to become stuck.
- 5 January 2023
- Published by Wiley in Journal of Field Robotics
- Vol. 40 (3) , 595-613
Reliable Monte Carlo localization for mobile robots
Reliability is a key factor for realizing safety guarantee of fully autonomous robot systems. In this paper, we focus on reliability in mobile robot localization. Monte Carlo localization (MCL) is widely used for mobile robot localization. However, it is still difficult to guarantee its safety because there are no methods determining reliability for MCL estimate. This paper presents a novel localization framework that enables robust localization, reliability estimation, and quick relocalization, simultaneously. The presented method can be implemented using a similar estimation manner to that of MCL. The method can increase localization robustness to environment changes by estimating known and unknown obstacles while performing localization; however, localization failure of course occurs by unanticipated errors. The method also includes a reliability estimation function that enables a robot to know whether localization has failed. Additionally, the method can seamlessly integrate a global localization method via importance sampling. Consequently, quick relocalization from a failure state can be realized while mitigating noisy influence of global localization. We conduct three types of experiments using wheeled mobile robots equipped with a two‐dimensional LiDAR. Results show that reliable MCL that performs robust localization, self‐failure detection, and quick failure recovery can be realized.
- 5 January 2023
- Published by Wiley in Journal of Field Robotics
- Vol. 40 (3) , 595-613
Reliable Monte Carlo localization for mobile robots
Reliability is a key factor for realizing safety guarantee of fully autonomous robot systems. In this paper, we focus on reliability in mobile robot localization. Monte Carlo localization (MCL) is widely used for mobile robot localization. However, it is still difficult to guarantee its safety because there are no methods determining reliability for MCL estimate. This paper presents a novel localization framework that enables robust localization, reliability estimation, and quick relocalization, simultaneously. The presented method can be implemented using a similar estimation manner to that of MCL. The method can increase localization robustness to environment changes by estimating known and unknown obstacles while performing localization; however, localization failure of course occurs by unanticipated errors. The method also includes a reliability estimation function that enables a robot to know whether localization has failed. Additionally, the method can seamlessly integrate a global localization method via importance sampling. Consequently, quick relocalization from a failure state can be realized while mitigating noisy influence of global localization. We conduct three types of experiments using wheeled mobile robots equipped with a two‐dimensional LiDAR. Results show that reliable MCL that performs robust localization, self‐failure detection, and quick failure recovery can be realized.
- Open Access
Reliable Monte Carlo Localization for Mobile Robots
Reliability is a key factor for realizing safety guarantee of full autonomous robot systems. In this paper, we focus on reliability in mobile robot localization. Monte Carlo localization (MCL) is widely used for mobile robot localization. However, it is still difficult to guarantee its safety because there are no methods determining reliability for MCL estimate. This paper presents a novel localization framework that enables robust localization, reliability estimation, and quick re-localization, simultaneously. The presented method can be implemented using similar estimation manner to that of MCL. The method can increase localization robustness to environment changes by estimating known and unknown obstacles while performing localization; however, localization failure of course occurs by unanticipated errors. The method also includes a reliability estimation function that enables us to know whether localization has failed. Additionally, the method can seamlessly integrate a global localization method via importance sampling. Consequently, quick re-localization from failures can be realized while mitigating noisy influence of global localization. Through three types of experiments, we show that reliable MCL that performs robust localization, self-failure detection, and quick failure recovery can be realized.
Open AccessReliable Monte Carlo Localization for Mobile Robots
Reliability is a key factor for realizing safety guarantee of full autonomous robot systems. In this paper, we focus on reliability in mobile robot localization. Monte Carlo localization (MCL) is widely used for mobile robot localization. However, it is still difficult to guarantee its safety because there are no methods determining reliability for MCL estimate. This paper presents a novel localization framework that enables robust localization, reliability estimation, and quick re-localization, simultaneously. The presented method can be implemented using similar estimation manner to that of MCL. The method can increase localization robustness to environment changes by estimating known and unknown obstacles while performing localization; however, localization failure of course occurs by unanticipated errors. The method also includes a reliability estimation function that enables us to know whether localization has failed. Additionally, the method can seamlessly integrate a global localization method via importance sampling. Consequently, quick re-localization from failures can be realized while mitigating noisy influence of global localization. Through three types of experiments, we show that reliable MCL that performs robust localization, self-failure detection, and quick failure recovery can be realized.
- 13 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (10) , 17130-17142
Detection of Localization Failures Using Markov Random Fields With Fully Connected Latent Variables for Safe LiDAR-Based Automated Driving
Most of the recent automated driving systems assume the accurate functioning of localization. Unanticipated errors cause localization failures and result in failures in automated driving. An exact localization failure detection is necessary to ensure safety in automated driving; however, detection of the localization failures is challenging because sensor measurement is assumed to be independent of each other in the localization process. Owing to the assumption, the entire relation of the sensor measurement is ignored. Consequently, it is difficult to recognize the misalignment between the sensor measurement and the map when partial sensor measurement overlaps with the map. This paper proposes a method for the detection of localization failures using Markov random fields with fully connected latent variables. The full connection enables to take the entire relation into account and contributes to the exact misalignment recognition. Additionally, this paper presents localization failure probability calculation and efficient distance field representation methods. We evaluate the proposed method using two types of datasets. The first dataset is the SemanticKITTI dataset, whereby four methods are compared with the proposed method. The comparison results reveal that the proposed method achieves the most accurate failure detection. The second dataset is created based on log data acquired from the demonstrations that we conducted in Japanese public roads. The dataset includes several localization failure scenes. We apply the failure detection methods to the dataset and confirm that the proposed method achieves exact and immediate failure detection.
- 13 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (10) , 17130-17142
Detection of Localization Failures Using Markov Random Fields With Fully Connected Latent Variables for Safe LiDAR-Based Automated Driving
Most of the recent automated driving systems assume the accurate functioning of localization. Unanticipated errors cause localization failures and result in failures in automated driving. An exact localization failure detection is necessary to ensure safety in automated driving; however, detection of the localization failures is challenging because sensor measurement is assumed to be independent of each other in the localization process. Owing to the assumption, the entire relation of the sensor measurement is ignored. Consequently, it is difficult to recognize the misalignment between the sensor measurement and the map when partial sensor measurement overlaps with the map. This paper proposes a method for the detection of localization failures using Markov random fields with fully connected latent variables. The full connection enables to take the entire relation into account and contributes to the exact misalignment recognition. Additionally, this paper presents localization failure probability calculation and efficient distance field representation methods. We evaluate the proposed method using two types of datasets. The first dataset is the SemanticKITTI dataset, whereby four methods are compared with the proposed method. The comparison results reveal that the proposed method achieves the most accurate failure detection. The second dataset is created based on log data acquired from the demonstrations that we conducted in Japanese public roads. The dataset includes several localization failure scenes. We apply the failure detection methods to the dataset and confirm that the proposed method achieves exact and immediate failure detection.
- 9 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 754-759
Bayesian Filtering Fusion of Optimization-Based Monocular Visual Localization and Autonomous Quadcopter Navigation
Visual localization is typically implemented using optimization algorithms. Because the optimization minimizes a cost function, their estimate is sensitive to noises, and estimated trajectory is usually jerk. The estimate can be fused with other estimates using Bayesian filter (BF) and smooth trajectory can be obtained; however, the optimization-based localization does not estimate uncertainty. In this study, we present an uncertainty estimation method for the optimization-based localization using Hessian matrix. The Hessian matrix is used in Newton method to calculate the increment. The increment is obtained by multiplying the inverse of Hessian and the gradient of the cost function. We consider that the inverse of Hessian could be used to indicate variability of the optimized states, and determine the uncertainty. We determine normal distribution over the estimate by the optimization-based localization and its uncertainty, that is, covariance, is determined using Hessian. In the experiment, we validate the uncertainty estimation method under different measurement conditions, and the effectiveness of the fusion using BF. Results show that the uncertainty can be appropriately estimated according to the conditions, and smooth trajectory can be estimated while maintaining the tracking accuracy to the visual localization result. Furthermore, we conduct autonomous flight navigation experiment with a quadcopter based on the presented localization, and its navigation is successfully performed. The software used in this work is publicly available.
- 9 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 754-759
Bayesian Filtering Fusion of Optimization-Based Monocular Visual Localization and Autonomous Quadcopter Navigation
Visual localization is typically implemented using optimization algorithms. Because the optimization minimizes a cost function, their estimate is sensitive to noises, and estimated trajectory is usually jerk. The estimate can be fused with other estimates using Bayesian filter (BF) and smooth trajectory can be obtained; however, the optimization-based localization does not estimate uncertainty. In this study, we present an uncertainty estimation method for the optimization-based localization using Hessian matrix. The Hessian matrix is used in Newton method to calculate the increment. The increment is obtained by multiplying the inverse of Hessian and the gradient of the cost function. We consider that the inverse of Hessian could be used to indicate variability of the optimized states, and determine the uncertainty. We determine normal distribution over the estimate by the optimization-based localization and its uncertainty, that is, covariance, is determined using Hessian. In the experiment, we validate the uncertainty estimation method under different measurement conditions, and the effectiveness of the fusion using BF. Results show that the uncertainty can be appropriately estimated according to the conditions, and smooth trajectory can be estimated while maintaining the tracking accuracy to the visual localization result. Furthermore, we conduct autonomous flight navigation experiment with a quadcopter based on the presented localization, and its navigation is successfully performed. The software used in this work is publicly available.
- 4 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 1431-1438
Mobile Robot Localization Considering Uncertainty of Depth Regression From Camera Images
This letter presents a mobile robot localization method that uses depth regression from camera images. In this work, we use convolutional neural networks to regress the depth from the camera images. However, the depth regression results contain uncertainty, which must be resolved to stably perform localization with the depth regression results. This letter proposes a novel probabilistic model that enables the handling of the uncertainty of the depth regression results while localizing the robot pose. By handling the uncertainty, inaccurate depth regression results can be ignored, and localization robustness can be increased. We compare the proposed method with two traditional methods used in particle-filter-based localization that do not handle depth regression uncertainty. Comparison experiments are performed using two types of datasets: a manually created dataset using only a visual inertial odometry sensor, and the KITTI odometry dataset. Results show that the proposed method can track the robot pose even though the depth regression results are inaccurate and can increase localization accuracy without increasing memory and computational costs.
- 4 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 1431-1438
Mobile Robot Localization Considering Uncertainty of Depth Regression From Camera Images
This letter presents a mobile robot localization method that uses depth regression from camera images. In this work, we use convolutional neural networks to regress the depth from the camera images. However, the depth regression results contain uncertainty, which must be resolved to stably perform localization with the depth regression results. This letter proposes a novel probabilistic model that enables the handling of the uncertainty of the depth regression results while localizing the robot pose. By handling the uncertainty, inaccurate depth regression results can be ignored, and localization robustness can be increased. We compare the proposed method with two traditional methods used in particle-filter-based localization that do not handle depth regression uncertainty. Comparison experiments are performed using two types of datasets: a manually created dataset using only a visual inertial odometry sensor, and the KITTI odometry dataset. Results show that the proposed method can track the robot pose even though the depth regression results are inaccurate and can increase localization accuracy without increasing memory and computational costs.