Seyed Amir Tafrishi

Qingmeng Wen, Yu-Kun Lai, Ze Ji et al.

Skeletonization is a powerful tool for shape analysis, rooted in the inherent instinct to understand an object's morphology. It has found applications across various domains, including robotics. Although skeletonization algorithms have been studied in recent years, their performance is rarely quantified with detailed numerical evaluations. This work focuses on defining and quantifying geometric properties to systematically score the skeletonization results of point cloud shapes across multiple aspects, including topological similarity, boundedness, centeredness, and smoothness. We introduce these representative metric definitions along with a numerical scoring framework to analyze skeletonization outcomes concerning point cloud data for different scenarios, from object manipulation to mobile robot navigation. Additionally, we provide an open-source tool to enable the research community to evaluate and refine their skeleton models. Finally, we assess the performance and sensitivity of the proposed geometric evaluation methods from various robotic applications.

Seyed Amir Tafrishi, Ankit A. Ravankar, Jose Salazar et al.

Certain wheeled mobile robots e.g., electric wheelchairs, can operate through indirect joystick controls from users. Correct steering angle becomes essential when the user should determine the vehicle direction and velocity, in particular for differential wheeled vehicles since the vehicle velocity and direction are controlled with only two actuating wheels. This problem gets more challenging when complex curves should be realized by the user. A novel assistive controller with safety constraints is needed to address these problems. Also, the classic control methods mostly require the desired states beforehand which completely contradicts human's spontaneous decisions on the desired location to go. In this work, we develop a novel assistive control strategy based on differential geometry relying on only joystick inputs and vehicle states where the controller does not require any desired states. We begin with explaining the vehicle kinematics and our designed Darboux frame kinematics on a contact point of a virtual wheel and plane. Next, the geometric controller using the Darboux frame kinematics is designed for having smooth trajectories under certain safety constraints. We experiment our approach with different participants and evaluate its performance in various routes.

Seyed Amir Tafrishi, Mikhail Svinin, Motoji Yamamoto et al.

The paper deals with motion planning for a spin-rolling sphere when the sphere follows a straight path on a plane. Since the motion of the sphere is constrained by the straight line, the control of the sphere's spin motion is essential to converge to a desired configuration of the sphere. In this paper, we show a new geometric-based planning approach that is based on a full-state description of this nonlinear system. First, the problem statement of the motion planning is posed. Next, we develop a geometric controller implemented as a virtual surface by using the Darboux frame kinematics. This virtual surface generates arc-length-based inputs for controlling the trajectories of the sphere. Then, an iterative algorithm is designed to tune these inputs for the desired configurations. The feasibility of the proposed approach is verified by simulations.

Seyed Amir Tafrishi, Mikhail Svinin, Motoji Yamamoto

This paper presents a new kinematic model based on the Darboux frame for motion control and planning. In this work, we show that an underactuated model of a spin-rolling sphere on a plane with five states and three inputs can be transformed into a fully-actuated one by a given Darboux frame transformation. This nonlinear state transformation establishes a geometric model that is different from conventional state-space ones. First, a kinematic model of the Darboux frame at the contact point of the rolling sphere is established. Next, we propose a virtual surface that is trapped between the sphere and the contact plane. This virtual surface is used for generating arc-length-based inputs for controlling the contact trajectories on the sphere and the plane. Finally, we discuss the controllability of this new model. In the future, we will design a geometric path planning method for the proposed kinematic model.

Seyed Amir Tafrishi, Xiaotian Dai, Vahid Esmaeilzadeh Kandjani

This paper presents a state-of-the-art filter that reduces the complexity in object detection, tracking and mapping applications. Existing edge detection and tracking methods are proposed to create suitable autonomy for mobile robots, however, many of them face overconfidence and large computations at the entrance to scenarios with an immense number of landmarks. The method in this work, the Line-Circle-Square (LCS) filter, claims that mobile robots without a large database for object recognition and highly advanced prediction methods can deal with incoming objects that the camera captures in real-time. The proposed filter applies detection, tracking and learning to each defined expert to extract higher level information for judging scenes without over-calculation. The interactive learning feed between each expert increases the consistency of detected landmarks that works against overwhelming detected features in crowded scenes. Our experts are dependent on trust factors' covariance under the geometric definitions to ignore, emerge and compare detected landmarks. The experiment validates the effectiveness of the proposed filter in terms of detection precision and resource usage in both experimental and real-world scenarios.

Seyed Amir Tafrishi, Mikhail Svinin, Motoji Yamamoto

Motion control of underactuated systems through the inverse dynamics contains configuration singularities. These limitations in configuration space mainly stem from the inertial coupling that passive joints/bodies create. In this study, we present a model that is free from singularity while the trajectory of the rotating mass has a small-amplitude sine wave around its circle. First, we derive the modified non-linear dynamics for a rolling system. Also, the singularity regions for this underactuated system is demonstrated. Then, the wave parameters are designed under certain conditions to remove the coupling singularities. We obtain these conditions from the positive definiteness of the inertia matrix in the inverse dynamics. Finally, the simulation results are confirmed by using a prescribed Beta function on the specified states of the rolling carrier. Because our algebraic method is integrated into the non-linear dynamics, the proposed solution has a great potential to be extended to the Lagrangian mechanics with multiple degrees-of-freedom.

Seyed Amir Tafrishi, Vahid E. Kandjani

This paper presents a state-of-the-art approach in object detection for being applied in future SLAM problems. Although, many SLAM methods are proposed to create suitable autonomy for mobile robots namely ground vehicles, they still face overconfidence and large computations during entrance to immense spaces with many landmarks. In particular, they suffer from impractical applications via sole reliance on the limited sensors like camera. Proposed method claims that unmanned ground vehicles without having huge amount of database for object definition and highly advance prediction parameters can deal with incoming objects during straight motion of camera in real-time. Line-Circle (LC) filter tries to apply detection, tracking and learning to each defined experts to obtain more information for judging scene without over-calculation. In this filter, circle expert let us summarize edges in groups. The Interactive feedback learning between each expert creates minimal error that fights against overwhelming landmark signs in crowded scenes without mapping. Our experts basically are dependent on trust factors' covariance with geometric definitions to ignore, emerge and compare detected landmarks. The experiment for validating the model is taken place utilizing a camera beside an IMU sensor for location estimation.

Seyed Amir Tafrishi, Sandor M. Veres, Esmaeil Esmaeilzadeh et al.

This paper introduces a simulation study of fluid actuated multi-driven closed system as spherical mobile robot called "RollRoller". Robot's mechanism design consists of two essential parts: tubes to lead a core and mechanical controlling parts to correspond movements. Our robot gets its motivation force by displacing the spherical movable mass known as core in curvy manners inside certain pipes. This simulation investigates by explaining the mechanical and structural features of the robot for creating hydraulic-base actuation via force and momentum analysis. Next, we categorize difficult and integrated 2D motions to omit unstable equilibrium points through derived nonlinear dynamics. We propose an algorithmic position control in forward direction that creates hybrid model as solution for motion planning problem in spherical robot. By deriving nonlinear dynamics of the spherical robot and implementing designed motion planning, we show how RollRoller can be efficient in high speed movements in comparison to the other pendulum-driven models. Then, we validate the results of this position control obtained by nonlinear dynamics via Adams/view simulation which uses the imported solid model of RollRoller. Lastly, We have a look to the circular maneuver of this robot by the same simulator.

Seyed Amir Tafrishi

This paper introduces novel air actuated spherical robot called "RollRoller". The RollRoller robot consists of two essential parts: tubes covered with a shell as a frame and mechanical controlling parts to correspond movements. The RollRoller is proposed to be high potential alternative for exploration and rescue missions robots because robot utilizing its locomotion via all possible deriving methods (gravity, torque and angular momentum forces). In beginning , characteristic and role of each of component and features were explained. Next, to determine the uniqueness of this robot, the known and other extra possible motions are shown by proposing their own algorithmic movements. To illustrate main motion of this robot was inherent to mathematical models, the forward direction dynamical behavior on flat surface was derived. Additionally, Matlab Simulink was used to plot the results to validate the behavior for both fractional and non-fractional terrains. Lastly, after designing the model of robot in Solidworks Program, Adams/View visualization software ( the robot simulated form ) was utilized to proof the Matlab Simulink results and to show the more detailed and complete form of locomotion including the forward direction and circular locomotion in proposed robot.