The document discusses various methods for robot navigation from simple to complex. It begins by explaining turtle graphics and sensor feedback methods. It then introduces using a coordinate system and estimating the robot's position to define waypoints and goals as coordinates. Commonly used waypoint navigation is explained along with automatic waypoint generation using RRT. Finally, it covers using graph searches like Dijkstra's algorithm and potential fields to optimize the path planning. The focus is on moving from object-based to coordinate-based representations and selecting rational routes.
Searching Behavior of a Simple Manipulator only with Sense of Touch Generated...Ryuichi Ueda
This document describes a study that uses probabilistic flow control (PFC) to generate search behavior in a simple robotic manipulator tasked with finding and grasping a fixed rod. PFC weights particles representing possible rod locations based on a value function, guiding the robot's motion in a search-like pattern as it taps and changes the direction of its arms while compensating for uncertainty in localizing the rod through touch sensing alone. The results demonstrate that PFC allows the robot to successfully complete the task through searching, while avoiding local minima issues, though longer completion times occur with higher weighting rates that prioritize exploration over exploitation. Future work will apply PFC to more practical cases and allow the weighting rate to vary.
This document summarizes an experiment using Particle Filter on Episode (PFoE) to teach and replay behaviors on a mobile robot. PFoE allows a robot to directly make decisions from recorded episodes of sensor values and actions without needing a map. In the experiment, a trainer used a gamepad to control the robot and teach it behaviors over three laps, which were recorded as an episode. During replay, the robot was able to reperform the taught behaviors in different sensory situations and properly alternate its goal, demonstrating PFoE can enable teach-and-replay with a simple algorithm.
The document discusses various methods for robot navigation from simple to complex. It begins by explaining turtle graphics and sensor feedback methods. It then introduces using a coordinate system and estimating the robot's position to define waypoints and goals as coordinates. Commonly used waypoint navigation is explained along with automatic waypoint generation using RRT. Finally, it covers using graph searches like Dijkstra's algorithm and potential fields to optimize the path planning. The focus is on moving from object-based to coordinate-based representations and selecting rational routes.
Searching Behavior of a Simple Manipulator only with Sense of Touch Generated...Ryuichi Ueda
This document describes a study that uses probabilistic flow control (PFC) to generate search behavior in a simple robotic manipulator tasked with finding and grasping a fixed rod. PFC weights particles representing possible rod locations based on a value function, guiding the robot's motion in a search-like pattern as it taps and changes the direction of its arms while compensating for uncertainty in localizing the rod through touch sensing alone. The results demonstrate that PFC allows the robot to successfully complete the task through searching, while avoiding local minima issues, though longer completion times occur with higher weighting rates that prioritize exploration over exploitation. Future work will apply PFC to more practical cases and allow the weighting rate to vary.
This document summarizes an experiment using Particle Filter on Episode (PFoE) to teach and replay behaviors on a mobile robot. PFoE allows a robot to directly make decisions from recorded episodes of sensor values and actions without needing a map. In the experiment, a trainer used a gamepad to control the robot and teach it behaviors over three laps, which were recorded as an episode. During replay, the robot was able to reperform the taught behaviors in different sensory situations and properly alternate its goal, demonstrating PFoE can enable teach-and-replay with a simple algorithm.
This study aims to develop an interactive idea-generation support system that enables users to consider the potential side effects of realizing new ideas.
In idea generation, confirmation bias often leads to an excessive focus on ``convenience,'' which can result in the oversight of unintended consequences, referred to as the ``side effects of convenience.''
To address this, we explored methods to alleviate user biases and expand perspectives through system-supported dialogue, facilitating a broader consideration of potential side effects.
The proposed system employs a stepwise idea-generation process supported by large language models (LLMs), enabling users to refine their ideas interactively.
By dividing the ideation process into distinct stages, the system mitigates biases at each stage while promoting ideas' concretization and identifying side effects through visually supported dialogues.
Preliminary evaluation suggests that engaging with the proposed system fosters awareness of diverse perspectives on potential side effects and facilitates the generation of ideas that proactively address these issues.
論文紹介:「Amodal Completion via Progressive Mixed Context Diffusion」「Amodal Insta...Toru Tamaki
Katherine Xu, Lingzhi Zhang, Jianbo Shi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, "Amodal Completion via Progressive Mixed Context Diffusion"CVPR2024
https://openaccess.thecvf.com/content/CVPR2024/html/Xu_Amodal_Completion_via_Progressive_Mixed_Context_Diffusion_CVPR_2024_paper.html
Minh Tran, Khoa Vo, Tri Nguyen, and Ngan Le,"Amodal Instance Segmentation with Diffusion Shape Prior Estimation"ACCV 2024
https://uark-aicv.github.io/AISDiff/