Model-based reinforcement learning (MBRL) has shown promise for improving sample efficiency and decision-making in complex environments. However, existing methods face challenges in training stability, robustness to noise, and computational efficiency. In this paper, we propose Bisimulation Metric for Model Predictive Control (BS-MPC), a novel approach that incorporates bisimulation metric loss in its objective function to directly optimize the encoder. This optimization enables the learned encoder to extract intrinsic information from the original state space while discarding irrelevant details. BS-MPC improves training stability, robustness against input noise, and computational efficiency by reducing training time. We evaluate BS-MPC on both continuous control and image-based tasks from the DeepMind Control Suite, demonstrating superior performance and robustness compared to state-of-the-art baseline methods.

This paper develops a new nonlinear filter, called Moment-based Kalman Filter (MKF), using the exact moment propagation method. Existing state estimation methods use linearization techniques or sampling points to compute approximate values of moments. However, moment propagation of probability distributions of random variables through nonlinear process and measurement models play a key role in the development of state estimation and directly affects their performance. The proposed moment propagation procedure can compute exact moments for non-Gaussian as well as non-independent Gaussian random variables. Thus, MKF can propagate exact moments of uncertain state variables up to any desired order. MKF is derivative-free and does not require tuning parameters. Moreover, MKF has the same computation time complexity as the extended or unscented Kalman filters, i.e., EKF and UKF. The experimental evaluations show that MKF is the preferred filter in comparison to EKF and UKF and outperforms both filters in non-Gaussian noise regimes.

Velocity Planning for self-driving vehicles in a complex environment is one of the most challenging tasks. It must satisfy the following three requirements: safety with regards to collisions; respect of the maximum velocity limits defined by the traffic rules; comfort of the passengers. In order to achieve these goals, the jerk and dynamic objects should be considered, however, it makes the problem as complex as a non-convex optimization problem. In this paper, we propose a linear programming (LP) based velocity planning method with jerk limit and obstacle avoidance constraints for an autonomous driving system. To confirm the efficiency of the proposed method, a comparison is made with several optimization-based approaches, and we show that our method can generate a velocity profile which satisfies the aforementioned requirements more efficiently than the compared methods. In addition, we tested our algorithm on a real vehicle at a test field to validate the effectiveness of the proposed method.

Motion planning under uncertainty is of significant importance for safety-critical systems such as autonomous vehicles. Such systems have to satisfy necessary constraints (e.g., collision avoidance) with potential uncertainties coming from either disturbed system dynamics or noisy sensor measurements. However, existing motion planning methods cannot efficiently find the robust optimal solutions under general nonlinear and non-convex settings. In this paper, we formulate such problem as chance-constrained Gaussian belief space planning and propose the constrained iterative Linear Quadratic Gaussian (CILQG) algorithm as a real-time solution. In this algorithm, we iteratively calculate a Gaussian approximation of the belief and transform the chance-constraints. We evaluate the effectiveness of our method in simulations of autonomous driving planning tasks with static and dynamic obstacles. Results show that CILQG can handle uncertainties more appropriately and has faster computation time than baseline methods.

This study is the development of the interface for visually handicapped persons using the knowledge of the robotics field. A basic device combining a tactile graphic display function and a touch position/force direction sensing function is proposed. The trial device consists of two major components, a tactile graphic display and a 6-axis force/torque sensor. The force sensor measures six dynamic values generated by touch action on the display surface and a PC estimates the point based on the data. The fundamental function for achieving the interactive communication is to detect the location where user is touching a tangible surface. By applying this functions, the click and scroll function by an empty hand are realized. In addition, an audio-tactile graphic system which can be used mainly to overcome tactile cognitive limitation is implemented as an application of the system. The validity of the developed tactile graphic system has been confirmed through subjective experiments.

It is important to analyze existing products of competitors when a product planner develops new products. In this research, we proposed a method of extracting product trend keywords from press releases to support product strategy analysis. In order to extract keywords from press releases, we utilize expression phrases which are defined as description patterns. A description pattern enables extracting keywords describing features of a product that cannot be extracted by using simply word frequency. Additionally, we utilize derivation patterns, which are expression phrases derived from a description pattern, to extract keywords more flexibly. Also to grasp time-series movement in the feature of each product, product feature trend map is discussed.