About

Abdeslam Boularias is an Associate Professor in the Department of Computer Science at Rutgers, The State University of New Jersey. His research group focuses on Artificial Intelligence, Intelligent Systems, and Robotics. He has received recognition for his work, including an NSF CAREER award, and has been involved in collaborative projects with Yale. Boularias has contributed to the field through research in cognitive robotics and related areas, and his work has been highlighted in various NSF grants and awards.

Research topics

• Computer Science
• Artificial Intelligence
• Computer vision
• Simulation
• Human–computer interaction

Selected publications

• Learning Visual Feature-Based World Models via Residual Latent Action

  arXiv (Cornell University) · 2026-05-08

  preprintOpen accessSenior author

  World models predict future transitions from observations and actions. Existing works predominantly focus on image generation only. Visual feature-based world models, on the other hand, predict future visual features instead of raw video pixels, offering a promising alternative that is more efficient and less prone to hallucination. However, current feature-based approaches rely on direct regression, which leads to blurry or collapsed predictions in complex interactions, while generative modeling in high-dimensional feature spaces still remains challenging. In this work, we discover that a new type of latent action representation, which we refer to as *Residual Latent Action* (RLA), can be easily learned from DINO residuals. We also show that RLA is predictive, generalizable, and encodes temporal progression. Building on RLA, we propose *RLA World Model* (RLA-WM), which predicts RLA values via flow matching. RLA-WM outperforms both state-of-the-art feature-based and video-diffusion world models on simulation and real-world datasets, while being orders of magnitude faster than video diffusion. Furthermore, we develop two robot learning techniques that use RLA-WM to improve policy learning. The first one is a minimalist world action model with RLA that learns from actionless demonstration videos. The second one is the first visual RL framework trained entirely inside a world model learned from offline videos only, using a video-aligned reward and no online interactions or handcrafted rewards. Project page: https://mlzxy.github.io/rla-wm

  PublisherDOI

• Learning Visual Feature-Based World Models via Residual Latent Action

  ArXiv.org · 2026-05-08

  articleOpen accessSenior author

  World models predict future transitions from observations and actions. Existing works predominantly focus on image generation only. Visual feature-based world models, on the other hand, predict future visual features instead of raw video pixels, offering a promising alternative that is more efficient and less prone to hallucination. However, current feature-based approaches rely on direct regression, which leads to blurry or collapsed predictions in complex interactions, while generative modeling in high-dimensional feature spaces still remains challenging. In this work, we discover that a new type of latent action representation, which we refer to as *Residual Latent Action* (RLA), can be easily learned from DINO residuals. We also show that RLA is predictive, generalizable, and encodes temporal progression. Building on RLA, we propose *RLA World Model* (RLA-WM), which predicts RLA values via flow matching. RLA-WM outperforms both state-of-the-art feature-based and video-diffusion world models on simulation and real-world datasets, while being orders of magnitude faster than video diffusion. Furthermore, we develop two robot learning techniques that use RLA-WM to improve policy learning. The first one is a minimalist world action model with RLA that learns from actionless demonstration videos. The second one is the first visual RL framework trained entirely inside a world model learned from offline videos only, using a video-aligned reward and no online interactions or handcrafted rewards. Project page: https://mlzxy.github.io/rla-wm

  PublisherOA PDF

• Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves

  arXiv (Cornell University) · 2026-03-21

  articleOpen access

  Understanding hand-object interaction (HOI) is fundamental to computer vision, robotics, and AR/VR. However, conventional hand videos often lack essential physical information such as contact forces and motion signals, and are prone to frequent occlusions. To address the challenges, we present Glove2Hand, a framework that translates multi-modal sensing glove HOI videos into photorealistic bare hands, while faithfully preserving the underlying physical interaction dynamics. We introduce a novel 3D Gaussian hand model that ensures temporal rendering consistency. The rendered hand is seamlessly integrated into the scene using a diffusion-based hand restorer, which effectively handles complex hand-object interactions and non-rigid deformations. Leveraging Glove2Hand, we create HandSense, the first multi-modal HOI dataset featuring glove-to-hand videos with synchronized tactile and IMU signals. We demonstrate that HandSense significantly enhances downstream bare-hand applications, including video-based contact estimation and hand tracking under severe occlusion.

  PublisherOA PDF

• KARL: Kalman-Filter Assisted Reinforcement Learner for Dynamic Object Tracking and Grasping

  2025-10-19 · 1 citations

  article

  We present Kalman-Filter Assisted Reinforcement Learner (KARL) for dynamic object tracking and grasping over eye-on-hand (EoH) systems, significantly expanding such systems’ capabilities in challenging, realistic environments. In comparison to the previous state-of-the-art, KARL (1) incorporates a novel six-stage RL curriculum that doubles the system’s motion range, thereby greatly enhancing the system’s grasping performance, (2) integrates a robust Kalman filter layer between the perception and reinforcement learning (RL) control modules, enabling the system to maintain an uncertain but continuous 6D pose estimate even when the target object temporarily exits the camera’s field-of-view or undergoes rapid, unpredictable motion, and (3) introduces mechanisms to allow retries to gracefully recover from unavoidable policy execution failures. Extensive evaluations conducted in both simulation and real-world experiments qualitatively and quantitatively corroborate KARL’s advantage over earlier systems, achieving higher grasp success rates and faster robot execution speed. Source code and supplementary materials for KARL will be made available at: https://github.com/arc-l/karl.

  PublisherDOI

• PROBE: Proprioceptive Obstacle Detection and Estimation while Navigating in Clutter

  2025-05-19

  articleSenior author

  In critical applications, including search-and-rescue in degraded environments, blockages can be prevalent and prevent the effective deployment of certain sensing modalities, particularly vision, due to occlusion and the constrained range of view of onboard camera sensors. To enable robots to tackle these challenges, we propose a new approach, Proprioceptive Obstacle Detection and Estimation while navigating in clutter (PROBE), which instead relies only on the robot's proprioception to infer the presence or absence of occluded rectangular obstacles while predicting their dimensions and poses in SE (2). The proposed approach is a Transformer neural network that receives as input a history of applied torques and sensed whole-body movements of the robot and returns a parameterized representation of the obstacles in the environment. The effectiveness of PROBE is evaluated on simulated environments in Isaac Gym and with a real Unitree Go1 quadruped robot. The project webpage can be found at https://dhruvmetha.github.io/legged-probe/.

  PublisherDOI

• Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policies

  2025-10-19

  articleSenior author

  This paper addresses the challenges of Rhythmic Insertion Tasks (RIT), where a robot must repeatedly perform high-precision insertions, such as screwing a nut into a bolt with a wrench. The inherent difficulty of RIT lies in achieving millimeter-level accuracy and maintaining consistent performance over multiple repetitions, particularly when factors like nut rotation and friction introduce additional complexity. We propose a sim-to-real framework that integrates a reinforcement learning-based insertion policy with a failure forecasting module. By representing the wrench’s pose in the nut’s coordinate frame rather than the robot’s frame, our approach significantly enhances sim-to-real transferability. The insertion policy, trained in simulation, leverages real-time 6D pose tracking to execute precise alignment, insertion, and rotation maneuvers. Simultaneously, a neural network predicts potential execution failures, triggering a simple recovery mechanism that lifts the wrench and retries the insertion. Extensive experiments in both simulated and real-world environments demonstrate that our method not only achieves a high one-time success rate but also robustly maintains performance over long-horizon repetitive tasks. For more information please refer to the website: jaysparrow.github.io/rit.

  PublisherDOI

• Integrating Model-Based Control and RL for Sim2Real Transfer of Tight Insertion Policies

  2025-05-19 · 1 citations

  article

  Object insertion under tight tolerances (<Imm) is an important but challenging assembly task as even small errors can result in undesirable contacts. Recent efforts focused on Reinforcement Learning (RL), which often depends on careful definition of dense reward functions. This work proposes an effective strategy for such tasks that integrates traditional model-based control with RL to achieve improved insertion accuracy. The policy is trained exclusively in simulation and is zero-shot transferred to the real system. It employs a potential field-based controller to acquire a model-based policy for inserting a plug into a socket given full observability in simulation. This policy is then integrated with residual RL, which is trained in simulation given only a sparse, goal-reaching reward. A curriculum scheme over observation noise and action magnitude is used for training the residual RL policy. Both policy components use as input the SE(3) poses of both the plug and the socket and return the plug's SE (3) pose transform, which is executed by a robotic arm using a controller. The integrated policy is deployed on the real system without further training or fine-tuning, given a visual SE (3) object tracker. The proposed solution and alternatives are evaluated across a variety of objects and conditions in simulation and reality. The proposed approach outperforms recent RL-based methods in this domain and prior efforts with hybrid policies. Ablations highlight the impact of each component of the approach. For more information please refer to the corresponding website.

  PublisherDOI

• PROBE: Proprioceptive Obstacle Detection and Estimation while Navigating in Clutter

  ArXiv.org · 2025-05-17

  preprintOpen accessSenior author

  In critical applications, including search-and-rescue in degraded environments, blockages can be prevalent and prevent the effective deployment of certain sensing modalities, particularly vision, due to occlusion and the constrained range of view of onboard camera sensors. To enable robots to tackle these challenges, we propose a new approach, Proprioceptive Obstacle Detection and Estimation while navigating in clutter PROBE, which instead relies only on the robot's proprioception to infer the presence or absence of occluded rectangular obstacles while predicting their dimensions and poses in SE(2). The proposed approach is a Transformer neural network that receives as input a history of applied torques and sensed whole-body movements of the robot and returns a parameterized representation of the obstacles in the environment. The effectiveness of PROBE is evaluated on simulated environments in Isaac Gym and with a real Unitree Go1 quadruped robot.

  PublisherOA PDFDOI

• Bounding Distributional Shifts in World Modeling through Novelty Detection

  ArXiv.org · 2025-08-08

  preprintOpen accessSenior author

  Recent work on visual world models shows significant promise in latent state dynamics obtained from pre-trained image backbones. However, most of the current approaches are sensitive to training quality, requiring near-complete coverage of the action and state space during training to prevent divergence during inference. To make a model-based planning algorithm more robust to the quality of the learned world model, we propose in this work to use a variational autoencoder as a novelty detector to ensure that proposed action trajectories during planning do not cause the learned model to deviate from the training data distribution. To evaluate the effectiveness of this approach, a series of experiments in challenging simulated robot environments was carried out, with the proposed method incorporated into a model-predictive control policy loop extending the DINO-WM architecture. The results clearly show that the proposed method improves over state-of-the-art solutions in terms of data efficiency.

  PublisherOA PDFDOI

• Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policies

  ArXiv.org · 2025-07-09

  preprintOpen accessSenior author

  This paper addresses the challenges of Rhythmic Insertion Tasks (RIT), where a robot must repeatedly perform high-precision insertions, such as screwing a nut into a bolt with a wrench. The inherent difficulty of RIT lies in achieving millimeter-level accuracy and maintaining consistent performance over multiple repetitions, particularly when factors like nut rotation and friction introduce additional complexity. We propose a sim-to-real framework that integrates a reinforcement learning-based insertion policy with a failure forecasting module. By representing the wrench's pose in the nut's coordinate frame rather than the robot's frame, our approach significantly enhances sim-to-real transferability. The insertion policy, trained in simulation, leverages real-time 6D pose tracking to execute precise alignment, insertion, and rotation maneuvers. Simultaneously, a neural network predicts potential execution failures, triggering a simple recovery mechanism that lifts the wrench and retries the insertion. Extensive experiments in both simulated and real-world environments demonstrate that our method not only achieves a high one-time success rate but also robustly maintains performance over long-horizon repetitive tasks.

  PublisherOA PDFDOI

Recent grants

• RI: CAREER: Task-Oriented Model Identification for Robust Robotic Manipulation

  NSF · $536k · 2019–2025

• S&AS: FND: Reflective Learning of Stochastic Physical Models for Robust Manipulation

  NSF · $683k · 2017–2020

Frequent coauthors

• Kostas E. Bekris

  42 shared

• Chaitanya Mitash

  Amazon (United States)

  31 shared

• Jan Peters

  Technical University of Darmstadt

  21 shared

• Bowen Wen

  19 shared

• Chang‐Kyu Song

  Rutgers, The State University of New Jersey

  18 shared

• Liam Schramm

  16 shared

• Haonan Chang

  15 shared

• Rahul Shome

  14 shared

Education

• Ph.D., Computer Science

  Rutgers, The State University of New Jersey

Awards & honors

• NSF CAREER Award
• NSF NRI grant
• NSF SA&S grant