arXiv subjects

Tzu-Hsiang Lin

Publications and source records attributed to Tzu-Hsiang Lin.

14 recordsLinked to original sources

arXiv2026

SEAMLiS: Visibility-Aware Safety for Perception-Limited Multi-Robot Exploration

Autonomous exploration in unknown environments is typically driven by informative frontiers, viewpoints, or trajectories, while local safety controllers avoid obstacles represented in the current map. Under finite sensing range and limited field of view, this separation can be unsafe: an exploration stack may plan optimistically through unobserved space and steer the sensor toward information gain rather than along the direction of motion, causing hidden obstacles to be detected too late for bounded-actuation avoidance. This paper presents SEAMLiS (Safe Exploration for Autonomous Multi-Robot Systems Under Limited Sensing), a modular execution-layer safety framework for decentralized multi-robot exploration. SEAMLiS preserves the upstream exploration stack, including the goal allocator and local planner, and enforces safety at the execution layer through perception-aware attitude and positional filters. A gatekeeper-based attitude filter switches between a visibility-promoting yaw policy and a velocity-tracking backup policy to preserve visibility of the critical known-free/unknown boundary with sufficient braking margin. A Control Barrier Function (CBF)-based positional filter then avoids known obstacles, newly detected obstacles, and other robots. We provide sufficient collision-avoidance conditions and validate the framework in randomized simulation, Isaac Sim, and Crazyflie hardware experiments. Results show collision-free exploration across tested single- and multi-robot settings while retaining much of the efficiency of visibility-promoting yaw control.

cs.RO↗

arXiv2026

ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies

Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into task failure. Existing methods address this either by expanding the training distribution through expert corrections or synthetic augmentation, or by steering a frozen policy at test time with guidance from a learned model. The former can be expensive or assumption-dependent, while the latter discards the corrected trajectories after execution. We introduce ReGuide, a self-improving framework that treats guided rollouts as reusable on-policy recovery data. ReGuide first uses Phase-Conditioned Guidance (PCG) to generate corrective rollouts: it constructs phase-specific latent targets, applies guidance only in the drifted-but-recoverable regime, and guides through the estimated clean action to match the dynamics model's training distribution. Successful guided rollouts are then absorbed back into the policy through ReGuide-FT, which fine-tunes the current checkpoint, or ReGuide-FS, which retrains from scratch on the augmented dataset; the two can also be composed and iterated. On Robomimic Can, Square, Transport, and Tool Hang, ReGuide improves base-policy success by $1.3$--$7.7\times$, outperforms LPB in the test-time-only setting, and matched-data ablations show that the gains come from guided recovery data rather than additional rollouts alone.

cs.LG↗

arXiv2026

Optimistic World Models: Efficient Exploration in Model-Based Deep Reinforcement Learning

Efficient exploration remains a central challenge in reinforcement learning (RL), particularly in sparse-reward environments. We introduce Optimistic World Models (OWMs), a principled and scalable framework for optimistic exploration that brings classical reward-biased maximum likelihood estimation (RBMLE) from adaptive control into deep RL. In contrast to upper confidence bound (UCB)-style exploration methods, OWMs incorporate optimism directly into model learning by augmentation with an optimistic dynamics loss that biases imagined transitions toward higher-reward outcomes. This fully gradient-based loss requires neither uncertainty estimates nor constrained optimization. Our approach is plug-and-play with existing world model frameworks, preserving scalability while requiring only minimal modifications to standard training procedures. We instantiate OWMs within two state-of-the-art world model architectures, leading to Optimistic DreamerV3 and Optimistic STORM, which demonstrate significant improvements in sample efficiency and cumulative return compared to their baseline counterparts.

cs.LG↗

arXiv2025

SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving

Collaborative driving systems leverage vehicle-to-everything (V2X) communication across multiple agents to enhance driving safety and efficiency. Traditional V2X systems take raw sensor data, neural features, or perception results as communication media, which face persistent challenges, including high bandwidth demands, semantic loss, and interoperability issues. Recent advances investigate natural language as a promising medium, which can provide semantic richness, decision-level reasoning, and human-machine interoperability at significantly lower bandwidth. Despite great promise, this paradigm shift also introduces new vulnerabilities within language communication, including message loss, hallucinations, semantic manipulation, and adversarial attacks. In this work, we present the first systematic study of full-stack safety and security issues in natural-language-based collaborative driving. Specifically, we develop a comprehensive taxonomy of attack strategies, including connection disruption, relay/replay interference, content spoofing, and multi-connection forgery. To mitigate these risks, we introduce an agentic defense pipeline, which we call SafeCoop, that integrates a semantic firewall, language-perception consistency checks, and multi-source consensus, enabled by an agentic transformation function for cross-frame spatial alignment. We systematically evaluate SafeCoop in closed-loop CARLA simulation across 32 critical scenarios, achieving 69.15% driving score improvement under malicious attacks and up to 67.32% F1 score for malicious detection. This study provides guidance for advancing research on safe, secure, and trustworthy language-driven collaboration in transportation systems. Our project page is https://xiangbogaobarry.github.io/SafeCoop.

cs.CV↗

arXiv2025

A Dynamic Watermarking Technique for Matching Communication Addresses with Cars in a Visual Field

We consider a problem faced by an intelligent roadside unit (RSU) monitoring a roadway by a video camera. Suppose the RSU notices that a particular car in its visual field needs to execute a specific evasive maneuver to avoid danger. It would like to send a packet addressed to that particular car with this suggestion. The problem is that while all the cars are communicating with the RSU, the RSU does not know which car in the video is associated with what IP address. So, it does not know which IP address to send the packet to. Indeed, the problem of matching addresses with cars in the visual field is a fundamental open problem. We provide an active solution employing dynamic watermarking that was originally developed for the security of cyber-physical systems. This technique calls for a car to superpose a small random excitation onto its actuation commands for steering angle or throttle/brake positions. The car sends this random waveform to the RSU in a packet containing its IP address. By signal processing of the video stream of a car at the RSU it can verify whether it matches with the waveform in the packet and thereby associates that the IP address of the packet with that car in the visual field. The RSU thereby determines which IP address is associated with which car in its visual field. We present two demonstrations of performance. We demonstrate experimental results on a laboratory transportation automated vehicles, a vision system, and a network, as well as on the field with two passenger sedans in practice. The results demonstrate that employing the dynamic watermarking method enables an RSU to distinguish the communication of a target vehicle from that of other IP addresses of nearby vehicles.

eess.SP↗

arXiv2022

On Task-Adaptive Pretraining for Dialogue Response Selection

Recent advancements in dialogue response selection (DRS) are based on the \textit{task-adaptive pre-training (TAP)} approach, by first initializing their model with BERT~\cite{devlin-etal-2019-bert}, and adapt to dialogue data with dialogue-specific or fine-grained pre-training tasks. However, it is uncertain whether BERT is the best initialization choice, or whether the proposed dialogue-specific fine-grained learning tasks are actually better than MLM+NSP. This paper aims to verify assumptions made in previous works and understand the source of improvements for DRS. We show that initializing with RoBERTa achieve similar performance as BERT, and MLM+NSP can outperform all previously proposed TAP tasks, during which we also contribute a new state-of-the-art on the Ubuntu corpus. Additional analyses shows that the main source of improvements comes from the TAP step, and that the NSP task is crucial to DRS, different from common NLU tasks.

cs.CL↗

arXiv2021

Triple Attention Network architecture for MovieQA

Movie question answering, or MovieQA is a multimedia related task wherein one is provided with a video, the subtitle information, a question and candidate answers for it. The task is to predict the correct answer for the question using the components of the multimedia - namely video/images, audio and text. Traditionally, MovieQA is done using the image and text component of the multimedia. In this paper, we propose a novel network with triple-attention architecture for the inclusion of audio in the Movie QA task. This architecture is fashioned after a traditional dual attention network focused only on video and text. Experiments show that the inclusion of audio using the triple-attention network results provides complementary information for Movie QA task which is not captured by visual or textual component in the data. Experiments with a wide range of audio features show that using such a network can indeed improve MovieQA performance by about 7% relative to just using only visual features.

cs.MM↗

arXiv2021

BeamSurfer: Minimalist Beam Management of Mobile mm-Wave Devices

Management of narrow directional beams is critical for mm-wave communication systems. Translational or rotational motion of the user can cause misalignment of transmit and receive beams with the base station losing track of the mobile. Reacquiring the user can take about one second in 5G NewRadio systems and significantly impair performance of applications, besides being energy intensive. It is therefore important to manage beams to continually maintain high received signal strength and prevent outages. It is also important to be able to recover from sudden but transient blockage caused by a handor face interposed in the Line-of-Sight (LoS) path. This work presents a beam management protocol called BeamSurfer that is targeted to the use case of users walking indoors near a base station. It is designed to be minimalistic, employing only in-band information, and not requiring knowledge such as location or orientation of the mobile device or any additional sensors. Evaluations under pedestrian mobility show that96%of the time it employs beams that are within3dB of what an omniscient Oracle would have chosen as the pair of optimal transmit-receive LoS beams. It also recovers from transient LoS blockage by continuing to maintain control packet communication over a pre-selected reflected path that preserves time-synchronization with the base station, which allows it to rapidly recover to the LoS link as soon as it is unblocked

eess.SY↗

arXiv2021

Silent Tracker: In-band Beam Management for Soft Handover for mm-Wave Networks

In mm-wave networks, cell sizes are small due to high path and penetration losses. Mobiles need to frequently switch softly from one cell to another to preserve network connections and context. Each soft handover involves the mobile performing directional neighbor cell search, tracking cell beam, completing cell access request, and finally, context switching. The mobile must independently discover cell beams, derive timing information, and maintain beam alignment throughout the process to avoid packet loss and hard handover. We propose Silent tracker which enables a mobile to reliably manage handover events by maintaining an aligned beam until the successful handover completion. It is entirely in-band beam mechanism that does not need any side information. Experimental evaluations show that Silent Tracker maintains the mobile's receive beam aligned to the potential target base station's transmit beam till the successful conclusion of handover in three mobility scenarios: human walk, device rotation, and 20 mph vehicular speed.

eess.SY↗

arXiv2021

UNBLOCK: Low Complexity Transient Blockage Recovery for Mobile mm-Wave Devices

Directional radio beams are used in the mm-Wave band to combat the high path loss. The mm-Wave band also suffers from high penetration losses from drywall, wood, glass, concrete, etc., and also the human body. Hence, as a mobile user moves, the Line of Sight (LoS) path between the mobile and the Base Station (BS) can be blocked by objects interposed in the path, causing loss of the link. A mobile with a lost link will need to be re-acquired as a new user by initial access, a process that can take up to a second, causing disruptions to applications. UNBLOCK is a protocol that allows a mobile to recover from transient blockages, such as those caused by a human hand or another human walking into the line of path or other temporary occlusions by objects, which typically disappear within the order of $100$ ms, without having to go through re-acquisition. UNBLOCK is based on extensive experimentation in office type environments which has shown that while a LoS path is blocked, there typically exists a Non-LoS path, i.e., a reflected path through scatterers, with a loss within about $10$ dB of the LoS path. UNBLOCK proactively keeps such a NLoS path in reserve, to be used when blockage happens, typically without any warning. UNBLOCK uses this NLoS path to maintain time-synchronization with the BS until the blockage disappears, as well as to search for a better NLoS path if available. When the transient blockage disappears, it reestablishes LoS communication at the epochs that have been scheduled by the BS for communication with the mobile.

cs.NI↗

arXiv2020

Robust Handwriting Recognition with Limited and Noisy Data

Despite the advent of deep learning in computer vision, the general handwriting recognition problem is far from solved. Most existing approaches focus on handwriting datasets that have clearly written text and carefully segmented labels. In this paper, we instead focus on learning handwritten characters from maintenance logs, a constrained setting where data is very limited and noisy. We break the problem into two consecutive stages of word segmentation and word recognition respectively and utilize data augmentation techniques to train both stages. Extensive comparisons with popular baselines for scene-text detection and word recognition show that our system achieves a lower error rate and is more suited to handle noisy and difficult documents

cs.CV↗

arXiv2020

A Multimodal Dialogue System for Conversational Image Editing

In this paper, we present a multimodal dialogue system for Conversational Image Editing. We formulate our multimodal dialogue system as a Partially Observed Markov Decision Process (POMDP) and trained it with Deep Q-Network (DQN) and a user simulator. Our evaluation shows that the DQN policy outperforms a rule-based baseline policy, achieving 90\% success rate under high error rates. We also conducted a real user study and analyzed real user behavior.

cs.CL↗

arXiv2020

Adjusting Image Attributes of Localized Regions with Low-level Dialogue

Natural Language Image Editing (NLIE) aims to use natural language instructions to edit images. Since novices are inexperienced with image editing techniques, their instructions are often ambiguous and contain high-level abstractions that tend to correspond to complex editing steps to accomplish. Motivated by this inexperience aspect, we aim to smooth the learning curve by teaching the novices to edit images using low-level commanding terminologies. Towards this end, we develop a task-oriented dialogue system to investigate low-level instructions for NLIE. Our system grounds language on the level of edit operations, and suggests options for a user to choose from. Though compelled to express in low-level terms, a user evaluation shows that 25% of users found our system easy-to-use, resonating with our motivation. An analysis shows that users generally adapt to utilizing the proposed low-level language interface. In this study, we identify that object segmentation as the key factor to the user satisfaction. Our work demonstrates the advantages of the low-level, direct language-action mapping approach that can be applied to other problem domains beyond image editing such as audio editing or industrial design.

cs.CL↗

arXiv2016

Interactive Spoken Content Retrieval by Deep Reinforcement Learning

User-machine interaction is important for spoken content retrieval. For text content retrieval, the user can easily scan through and select on a list of retrieved item. This is impossible for spoken content retrieval, because the retrieved items are difficult to show on screen. Besides, due to the high degree of uncertainty for speech recognition, the retrieval results can be very noisy. One way to counter such difficulties is through user-machine interaction. The machine can take different actions to interact with the user to obtain better retrieval results before showing to the user. The suitable actions depend on the retrieval status, for example requesting for extra information from the user, returning a list of topics for user to select, etc. In our previous work, some hand-crafted states estimated from the present retrieval results are used to determine the proper actions. In this paper, we propose to use Deep-Q-Learning techniques instead to determine the machine actions for interactive spoken content retrieval. Deep-Q-Learning bypasses the need for estimation of the hand-crafted states, and directly determine the best action base on the present retrieval status even without any human knowledge. It is shown to achieve significantly better performance compared with the previous hand-crafted states.

cs.CL↗