arXiv subjects

Letian Chen

Publications and source records attributed to Letian Chen.

At least 37 records · Page 2Linked to original sources

arXiv2025

S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Modelwith Spatio-Temporal Visual Representation

The latest advancements in multi-modal large language models (MLLMs) have spurred a strong renewed interest in end-to-end motion planning approaches for autonomous driving. Many end-to-end approaches rely on human annotations to learn intermediate perception and prediction tasks, while purely self-supervised approaches--which directly learn from sensor inputs to generate planning trajectories without human annotations often underperform the state of the art. We observe a key gap in the input representation space: end-to-end approaches built on MLLMs are often pretrained with reasoning tasks in 2D image space rather than the native 3D space in which autonomous vehicles plan. To this end, we propose S4-Driver, a scalable self-supervised motion planning algorithm with spatio-temporal visual representation, based on the popular PaLI multimodal large language model. S4-Driver uses a novel sparse volume strategy to seamlessly transform the strong visual representation of MLLMs from perspective view to 3D space without the need to finetune the vision encoder. This representation aggregates multi-view and multi-frame visual inputs and enables better prediction of planning trajectories in 3D space. To validate our method, we run experiments on both nuScenes and Waymo Open Motion Dataset (with in-house camera data). Results show that S4-Driver performs favorably against existing supervised multi-task approaches while requiring no human annotations. It also demonstrates great scalability when pretrained on large volumes of unannotated driving logs.

cs.CV↗

arXiv2025

Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations

Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. However, current LfD frameworks are not capable of fast adaptation to heterogeneous human demonstrations nor the large-scale deployment in ubiquitous robotics applications. In this paper, we propose a novel LfD framework, Fast Lifelong Adaptive Inverse Reinforcement learning (FLAIR). Our approach (1) leverages learned strategies to construct policy mixtures for fast adaptation to new demonstrations, allowing for quick end-user personalization, (2) distills common knowledge across demonstrations, achieving accurate task inference; and (3) expands its model only when needed in lifelong deployments, maintaining a concise set of prototypical strategies that can approximate all behaviors via policy mixtures. We empirically validate that FLAIR achieves adaptability (i.e., the robot adapts to heterogeneous, user-specific task preferences), efficiency (i.e., the robot achieves sample-efficient adaptation), and scalability (i.e., the model grows sublinearly with the number of demonstrations while maintaining high performance). FLAIR surpasses benchmarks across three control tasks with an average 57% improvement in policy returns and an average 78% fewer episodes required for demonstration modeling using policy mixtures. Finally, we demonstrate the success of FLAIR in a table tennis task and find users rate FLAIR as having higher task (p<.05) and personalization (p<.05) performance.

cs.LG↗

arXiv2025

ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics

Reinforcement learning (RL) has demonstrated compelling performance in robotic tasks, but its success often hinges on the design of complex, ad hoc reward functions. Researchers have explored how Large Language Models (LLMs) could enable non-expert users to specify reward functions more easily. However, LLMs struggle to balance the importance of different features, generalize poorly to out-of-distribution robotic tasks, and cannot represent the problem properly with only text-based descriptions. To address these challenges, we propose ELEMENTAL (intEractive LEarning froM dEmoNstraTion And Language), a novel framework that combines natural language guidance with visual user demonstrations to align robot behavior with user intentions better. By incorporating visual inputs, ELEMENTAL overcomes the limitations of text-only task specifications, while leveraging inverse reinforcement learning (IRL) to balance feature weights and match the demonstrated behaviors optimally. ELEMENTAL also introduces an iterative feedback-loop through self-reflection to improve feature, reward, and policy learning. Our experiment results demonstrate that ELEMENTAL outperforms prior work by 42.3% on task success, and achieves 41.3% better generalization in out-of-distribution tasks, highlighting its robustness in LfD.

cs.RO↗

arXiv2025

A Mechanism-Guided Inverse Engineering Framework to Unlock Design Principles of H-Bonded Organic Frameworks for Gas Separation

The diverse combinations of novel building blocks offer a vast design space for hydrogen-boned frameworks (HOFs), rendering it a great promise for gas separation and purification. However, the underlying separation mechanism facilitated by their unique hydrogen-bond networks has not yet been fully understood. In this work, a comprehensive understanding of the separation mechanisms was achieved through an iterative data-driven inverse engineering approach established upon a hypothetical HOF database possessing nearly 110,000 structures created by a material genomics method. Leveraging a simple yet universal feature extracted from hydrogen bonding information with unambiguous physical meanings, the entire design space was exploited to rapidly identify the optimization route towards novel HOF structures with superior Xe/Kr separation performance (selectivity >103). This work not only provides the first large-scale HOF database, but also demonstrates the enhanced machine learning interpretability of our model-driven iterative inverse design framework, offering new insights into the rational design of nanoporous materials for gas separation.

physics.chem-ph↗

arXiv2025

Numerical investigation of the Brownian $q=2$ Potts Model

In active matter, such as the Vicsek Model of flocking, particles possesses an internal degree of freedom, such as their director, which is subject to interaction with other particles, provided they are within a certain range. In an effort to understand better the interplay between spatial and internal degrees of freedom, we study numerically a variation of the $q=2$ Potts Model on and off the lattice, where particles are additionally subject to Brownian motion. The lack of a feedback of the internal degrees of freedom to the spatial degrees of freedom renders this model generically non-equilibrium. We confirm previous work that showed that the static exponents of the phase transition are unaffected by the diffusion. In contrast to previous work, we show that the formation of ordered clusters is not undermined by diffusion, but should rather be thought of as an effective form of interaction. We demonstrate how our numerical findings can be understood on the basis of the well-established Model A, B and C: Off lattice, the Brownian $q=2$ Potts Model is Model C. On the lattice, it is Model A with an additional (irrelevant, conserved) Model B noise.

cond-mat.stat-mech↗

arXiv2024

A constant potential reactor framework for electrochemical reaction simulations

Understanding the evolution of electrified solid-liquid interfaces during electrochemical reactions is crucial. However, capturing the dynamic behavior of the interfaces with high temporal resolution and accuracy over long timescales remains a major challenge for both experimental and computational techniques. Here, we present a constant potential reactor framework that enables the simulation of electrochemical reactions with ab initio accuracy over extended timescales, allowing for real-time atomic scale observations for the electrified solid-liquid interface evolution. By implementing an enhanced sampling active learning protocol, we develop fast, accurate, and scalable neural network potentials that generalize across systems with varying electron counts, based on high-throughput density functional theory computations within an explicit-implicit hybrid solvent model. The simulation of reactions in realistic electrochemical environments uncovers the intrinsic mechanisms through which alkali metal cations promote CO2 adsorption and suppress the hydrogen evolution reaction. These findings align with previous experimental results and clarify previously elusive observations, offering valuable computational insights. Our framework lay the groundwork for future studies exploring the dynamic interplay between interfacial structure and reactivity in electrochemical environments.

physics.chem-ph↗

arXiv2024

Existence of monotone Morse flow lines of the expander functional

Given a smooth asymptotically conical self-expander that is strictly unstable we construct a (singular) Morse flow line of the expander functional that connects it to a stable self-expander. This flow is monotone in a suitable sense and has small singular set.

math.DG↗

arXiv2024

On the efficiency of an autonomous dynamic Szilard engine operating on a single active particle

The Szilard engine stands as a compelling illustration of the intricate interplay between information and thermodynamics. While at thermodynamic equilibrium, the apparent breach of the second law of thermodynamics was reconciled by Landauer and Bennett's insights into memory writing and erasure, recent extensions of these concepts into regimes featuring active fluctuations have unveiled the prospect of exceeding Landauer's bound, capitalizing on information to divert free energy from dissipation towards useful work. To explore this question further, we investigate an autonomous dynamic Szilard engine, addressing the thermodynamic consistency of work extraction and measurement costs by extending the phase space to incorporate an auxiliary system, which plays the role of an explicit measurement device. The nonreciprocal coupling between active particle and measurement device introduces a feedback control loop, and the cost of measurement is quantified through excess entropy production. The study considers different measurement scenarios, highlighting the role of measurement precision in determining engine efficiency.

cond-mat.stat-mech↗

arXiv2023

Interpretable Reinforcement Learning for Robotics and Continuous Control

Interpretability in machine learning is critical for the safe deployment of learned policies across legally-regulated and safety-critical domains. While gradient-based approaches in reinforcement learning have achieved tremendous success in learning policies for continuous control problems such as robotics and autonomous driving, the lack of interpretability is a fundamental barrier to adoption. We propose Interpretable Continuous Control Trees (ICCTs), a tree-based model that can be optimized via modern, gradient-based, reinforcement learning approaches to produce high-performing, interpretable policies. The key to our approach is a procedure for allowing direct optimization in a sparse decision-tree-like representation. We validate ICCTs against baselines across six domains, showing that ICCTs are capable of learning policies that parity or outperform baselines by up to 33% in autonomous driving scenarios while achieving a 300x-600x reduction in the number of parameters against deep learning baselines. We prove that ICCTs can serve as universal function approximators and display analytically that ICCTs can be verified in linear time. Furthermore, we deploy ICCTs in two realistic driving domains, based on interstate Highway-94 and 280 in the US. Finally, we verify ICCT's utility with end-users and find that ICCTs are rated easier to simulate, quicker to validate, and more interpretable than neural networks.

cs.RO↗

arXiv2023

Correlation, crossover and broken scaling in the Abelian Manna Model

The role of correlations in self-organised critical (SOC) phenomena is investigated by studying the Abelian Manna Model (AMM) in two dimensions. Local correlations of the debris left behind after avalanches are destroyed by re-arranging particles on the lattice between avalanches, without changing the one-point particle density. It is found that the spatial correlations are not relevant to small avalanches, while changing the scaling of the large (system-wide) ones, yielding a crossover in the model's scaling behaviour. This crossover breaks the simple scaling observed in normal SOC.

cond-mat.stat-mech↗

arXiv2023

Adversarial Search and Tracking with Multiagent Reinforcement Learning in Sparsely Observable Environment

We study a search and tracking (S&T) problem where a team of dynamic search agents must collaborate to track an adversarial, evasive agent. The heterogeneous search team may only have access to a limited number of past adversary trajectories within a large search space. This problem is challenging for both model-based searching and reinforcement learning (RL) methods since the adversary exhibits reactionary and deceptive evasive behaviors in a large space leading to sparse detections for the search agents. To address this challenge, we propose a novel Multi-Agent RL (MARL) framework that leverages the estimated adversary location from our learnable filtering model. We show that our MARL architecture can outperform all baselines and achieves a 46% increase in detection rate.

cs.LG↗

arXiv2023

Learning Models of Adversarial Agent Behavior under Partial Observability

The need for opponent modeling and tracking arises in several real-world scenarios, such as professional sports, video game design, and drug-trafficking interdiction. In this work, we present Graph based Adversarial Modeling with Mutal Information (GrAMMI) for modeling the behavior of an adversarial opponent agent. GrAMMI is a novel graph neural network (GNN) based approach that uses mutual information maximization as an auxiliary objective to predict the current and future states of an adversarial opponent with partial observability. To evaluate GrAMMI, we design two large-scale, pursuit-evasion domains inspired by real-world scenarios, where a team of heterogeneous agents is tasked with tracking and interdicting a single adversarial agent, and the adversarial agent must evade detection while achieving its own objectives. With the mutual information formulation, GrAMMI outperforms all baselines in both domains and achieves 31.68% higher log-likelihood on average for future adversarial state predictions across both domains.

cs.LG↗

arXiv2023

The Effect of Robot Skill Level and Communication in Rapid, Proximate Human-Robot Collaboration

As high-speed, agile robots become more commonplace, these robots will have the potential to better aid and collaborate with humans. However, due to the increased agility and functionality of these robots, close collaboration with humans can create safety concerns that alter team dynamics and degrade task performance. In this work, we aim to enable the deployment of safe and trustworthy agile robots that operate in proximity with humans. We do so by 1) Proposing a novel human-robot doubles table tennis scenario to serve as a testbed for studying agile, proximate human-robot collaboration and 2) Conducting a user-study to understand how attributes of the robot (e.g., robot competency or capacity to communicate) impact team dynamics, perceived safety, and perceived trust, and how these latent factors affect human-robot collaboration (HRC) performance. We find that robot competency significantly increases perceived trust ($p<.001$), extending skill-to-trust assessments in prior studies to agile, proximate HRC. Furthermore, interestingly, we find that when the robot vocalizes its intention to perform a task, it results in a significant decrease in team performance ($p=.037$) and perceived safety of the system ($p=.009$).

cs.RO↗

arXiv2023

Safe Inverse Reinforcement Learning via Control Barrier Function

Learning from Demonstration (LfD) is a powerful method for enabling robots to perform novel tasks as it is often more tractable for a non-roboticist end-user to demonstrate the desired skill and for the robot to efficiently learn from the associated data than for a human to engineer a reward function for the robot to learn the skill via reinforcement learning (RL). Safety issues arise in modern LfD techniques, e.g., Inverse Reinforcement Learning (IRL), just as they do for RL; yet, safe learning in LfD has received little attention. In the context of agile robots, safety is especially vital due to the possibility of robot-environment collision, robot-human collision, and damage to the robot. In this paper, we propose a safe IRL framework, CBFIRL, that leverages the Control Barrier Function (CBF) to enhance the safety of the IRL policy. The core idea of CBFIRL is to combine a loss function inspired by CBF requirements with the objective in an IRL method, both of which are jointly optimized via gradient descent. In the experiments, we show our framework performs safer compared to IRL methods without CBF, that is $\sim15\%$ and $\sim20\%$ improvement for two levels of difficulty of a 2D racecar domain and $\sim 50\%$ improvement for a 3D drone domain.

cs.RO↗

arXiv2023

Athletic Mobile Manipulator System for Robotic Wheelchair Tennis

Athletics are a quintessential and universal expression of humanity. From French monks who in the 12th century invented jeu de paume, the precursor to modern lawn tennis, back to the K'iche' people who played the Maya Ballgame as a form of religious expression over three thousand years ago, humans have sought to train their minds and bodies to excel in sporting contests. Advances in robotics are opening up the possibility of robots in sports. Yet, key challenges remain, as most prior works in robotics for sports are limited to pristine sensing environments, do not require significant force generation, or are on miniaturized scales unsuited for joint human-robot play. In this paper, we propose the first open-source, autonomous robot for playing regulation wheelchair tennis. We demonstrate the performance of our full-stack system in executing ground strokes and evaluate each of the system's hardware and software components. The goal of this paper is to (1) inspire more research in human-scale robot athletics and (2) establish the first baseline for a reproducible wheelchair tennis robot for regulation singles play. Our paper contributes to the science of systems design and poses a set of key challenges for the robotics community to address in striving towards robots that can match human capabilities in sports.

cs.RO↗

arXiv2022

Utilizing Human Feedback for Primitive Optimization in Wheelchair Tennis

Agile robotics presents a difficult challenge with robots moving at high speeds requiring precise and low-latency sensing and control. Creating agile motion that accomplishes the task at hand while being safe to execute is a key requirement for agile robots to gain human trust. This requires designing new approaches that are flexible and maintain knowledge over world constraints. In this paper, we consider the problem of building a flexible and adaptive controller for a challenging agile mobile manipulation task of hitting ground strokes on a wheelchair tennis robot. We propose and evaluate an extension to work done on learning striking behaviors using a probabilistic movement primitive (ProMP) framework by (1) demonstrating the safe execution of learned primitives on an agile mobile manipulator setup, and (2) proposing an online primitive refinement procedure that utilizes evaluative feedback from humans on the executed trajectories.

cs.RO↗

arXiv2022

Rotational symmetry of solutions of mean curvature flow coming out of a double cone II

We show that any integral Brakke flow coming out of a rotationally symmetric double cone with entropy at most two must stay rotationally symmetric for all time, provided the flow is smooth for a short time. We also show the existence of a non-self-similar flow coming out of a double cone with entropy at most two, and give an example of such a flow with a finite time singularity.

math.DG↗

arXiv2022

On the Existence and Uniqueness of Ancient Rescaled Mean Curvature Flows

We show existence of ancient solutions to the rescaled mean curvature flow starting from a given asymptotically conical self-expander. These are examples of mean curvature flows coming out of cones that are not self-similar. We also show a strong uniqueness theorem when the cone is generic and use it to classify mean curvature flows coming out of generic cones of small entropy in low dimensions.

math.DG↗