Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1607.04763

Design and implementation of computational platform for social-humanoid robot Lumen as an exhibition guide in Electrical Engineering Days 2015

Ahmad Syarif·Ary Setijadi Prihatmanto
View original source ↗Read source document ↗Export metadata ↓

Abstract

Social Robot Lumen is an Artificial Intelligence development project that aims to create an Artificial Intelligence (AI) which allows a humanoid robot to communicate with human being naturally. In this study, Lumen will be developed to be a tour guide in Electrical Engineering Days 2015 exhibition. In developing an AI, there are a lot of modules that need to be developed separately. To make the development easier, we need a computational platform which becomes basis for all developers to give easiness in developing the modules in parallel way. That computational platform that developed by the writer is called Lumen Server. Lumen Server has two main function, which are to be a bridge between all Lumen intelligence modules with NAO robot, and to be the communication bridge between those Lumen intelligence modules. For the second function, Lumen Server implements the AMQP protocol using RabbitMQ. Besides that, writer also developed a control system for robot movement called Lumen Motion. Lumen motion is implemented by modelling the movement of NAO robot and also by creating a control system using fuzzy logic controller. Writer also developed a program that connects all Lumen intelligence modules so that Lumen can act like a tour guide. The implementation of this program uses FSM and event-driven program. From implementation result, all the features which were designed are successfully implemented. By the developing of this computational platform, it can ease the development of Lumen in the future. For next development, it must be focused on creating integration system so that Lumen can be more responsive to the environment. ----- Sosial Robot Lumen adalah proyek pengembangan kecerdasan buatan yang bertujuan untuk menciptakan kecerdasan buatan atau artificial intelligence (AI) yang memungkinkan robot untuk dapat berkomunikasi dengan manusia secara alami.

Explore related subjects

cs.ROcs.HC

Keep this discovery

BibTeXRIS

Ahmad Syarif, Ary Setijadi Prihatmanto. 2016-07-16. Design and implementation of computational platform for social-humanoid robot Lumen as an exhibition guide in Electrical Engineering Days 2015. https://doi.org/10.13140/rg.2.1.2317.9762

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies

Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design couples this backbone with a dedicated continuous action head trained via diffusion or flow matching. However, such heads rely on iterative multi-step sampling, for example 10 Euler steps in $\pi_{0.5}$. This creates an inference bottleneck that produces stop-and-go movement in the robot and slower task completion. We introduce IMLE-VLA, which replaces the iterative action head with a single-step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE). The cIMLE objective promotes multimodal action coverage, avoiding the mode collapse of naive regression heads while eliminating multi-step sampling entirely. When IMLE-VLA is applied to $\pi_{0.5}$, it increases inference frequency 3.67x (55 Hz vs. 15 Hz), enabling up to 11x higher action throughput. On the 40-task LIBERO benchmark, IMLE-VLA achieves the highest average success rate (98.0%) among all baselines while leading in inference frequency. Under the test-time perturbations of LIBERO-plus, IMLE-VLA retains $\pi_{0.5}$'s robustness while other baselines degrade sharply, confirming that the cIMLE head preserves generalization. Real-world experiments on a Franka Emika Panda across four tasks demonstrate smoother motion (2.2x to 3.0x lower jerk) and faster task completion, with IMLE-VLA outperforming $\pi_{0.5}$ on every task and reducing average VLA inference time per episode by 3.9x to 6.6x. Videos and code are available at https://kianhk6.github.io/IMLE-VLA/

cs.RO↗
arXiv2026

ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations

Imitation learning has achieved impressive results in robotic manipulation, yet most existing approaches assume clean backgrounds and lack explicit mechanisms for obstacle-aware motion generation. Extending such policies to cluttered, real-world scenes with unstructured obstacles remains a key generalization challenge. We present ObstaDiff, a decomposed diffusion-policy framework with a lightweight obstacle-aware visual encoder. ObstaDiff extracts a structured target-obstacle-background representation, enabling the downstream alignment policy to generate end-effector trajectories toward a target-centered bottleneck pose while reasoning about surrounding obstacles. We evaluate ObstaDiff on 61 real-robot greenhouse trials per method (366 executions in total). ObstaDiff achieves 75.41% average task success and 8.20% average obstacle collision rate, outperforming representative imitation-learning baselines and improving generalization in cluttered agricultural scenes.

cs.RO↗
arXiv2026

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove

AI-based automated vehicle testing is challenging because a model that passes every test condition can still fail in the real world. Formal verification offers a way to directly address this gap. On a simulated highway and an arterial road we trained two small end-to-end steering networks each in CARLA, one on clear conditions alone and one on clear, fog, night and low sun. All four models were driven against a 2.19 ft lane-departure budget. Without driving again, we used bound propagation, a formal method that reads the trained weights, to compute how far steering can drift at every disturbance strength between two captured images. One calculation covers more than a campaign could drive: on the arterial it spans 133 poses, where ten intensities each would be 10^133 combinations, in minutes on one GPU. Not only did formal verification find conditions that broke the clear-trained policy without simulation testing, it provided some preliminary evidence for potential failures between the test cases. Our overall conclusion is that formal verification is a viable complement to simulation, and could be adopted as a part of verification and validation for automated driving.

cs.RO↗