arXiv subjects

Yash Jangir

Publications and source records attributed to Yash Jangir.

6 recordsLinked to original sources

arXiv2026

Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models

Action verbs describe not only the physical outcomes of actions, but also how those actions are performed. Yet action representations in vision-language-action models (VLAs) are typically optimized for reconstruction under L1/L2 losses in raw action space, where numerical proximity need not reflect linguistically meaningful distinctions. On BridgeV2, we show that action trajectories contain verb-grounding information beyond visual state changes, and that reconstruction-only discrete tokenization systematically erodes this information. To address this problem, we introduce SALT, a Semantically ALigned action Tokenizer that augments a VQ-VAE-style tokenizer with an auxiliary objective requiring a frozen vision-language model to recover the episode instruction from quantized action latents. Policies trained with SALT achieve 71.9% average success in SimplerEnv, compared with 42.7% for a reconstruction-only VQ-VAE tokenizer and 31.2% for FAST. SALT also develops verb-specialized codes while maintaining reconstruction fidelity. These results show that robot action trajectories provide a source of language grounding and that preserving this structure in action representations can substantially improve language-conditioned control.

cs.RO↗

arXiv2026

MotionForesight: Re-purposing Video Models for Future 3D Scene-Flow Prediction

Humans can infer how objects are likely to move from passive observation: a cup may be lifted, a drawer may slide, and a lid may rotate shut. Such predictions expose the physical consequences of interaction needed to act in the real world. We study how to learn this anticipation from ordinary monocular videos of human-object interaction. Given a short observed video context, MotionForesight predicts future 3D trajectories for points on the manipulated object. This casts interaction prediction as object-centered 3D motion forecasting without any assumptions on the object properties. Our key insight is that video prediction models already encode rich priors about how objects move during human interactions. We redirect these priors from pixel prediction toward future 3D scene flow. We start from a dense 3D tracker built on a pretrained video model, generate pseudo-ground-truth tracks from complete clips, and train the forecaster using only the observed frames. We replace future RGB and geometry with learned mask latents and train a lightweight adapter to turn the retrospective tracking representation into a forward predictor, while freezing the large video and tracking components. Using just 40k human videos and no auxiliary inputs such as language, MotionForesight generalizes across diverse out-of-distribution objects, environments, viewpoints, and interactions. It also outperforms substantially larger models that use over a million training videos. These results show that we can efficiently re-purpose video priors into explicit geometric forecasts for embodied intelligence. https://motionforesight.github.io/

cs.CV↗

arXiv2026

Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction

Multi-finger robotic hand manipulation and grasping are challenging due to the high-dimensional action space and the difficulty of acquiring large-scale training data. Existing approaches largely rely on human teleoperation with wearable devices or specialized sensing equipment to capture hand-object interactions, which limits scalability. In this work, we propose VIDEOMANIP, a device-free framework that learns dexterous manipulation directly from RGB human videos. Leveraging recent advances in computer vision, VIDEOMANIP reconstructs explicit 3D robot-object trajectories from monocular videos by estimating human hand poses, object meshes, and retargets the reconstructed human motions to robotic hands for manipulation learning. To make the reconstructed robot data suitable for dexterous manipulation training, we introduce hand-object contact optimization with interaction-centric grasp modeling, as well as a demonstration synthesis strategy that generates diverse training trajectories from a single video, enabling generalizable policy learning without additional robot demonstrations. In simulation, the learned grasping model achieves a 70.25% success rate across 20 diverse objects using the Inspire Hand. In the real world, manipulation policies trained from RGB videos achieve an average 62.86% success rate across seven tasks using the LEAP Hand, outperforming retargeting-based methods by 15.87%. Project videos are available at videomanip.github.io.

cs.RO↗

arXiv2025

RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation

The pursuit of robot generalists, agents capable of performing diverse tasks across diverse environments, demands rigorous and scalable evaluation. Yet real-world testing of robot policies remains fundamentally constrained: it is labor-intensive, slow, unsafe at scale, and difficult to reproduce. As policies expand in scope and complexity, these barriers only intensify, since defining "success" in robotics often hinges on nuanced human judgments of execution quality. We introduce RobotArena Infinity, a new benchmarking framework that overcomes these challenges by shifting vision-language-action (VLA) evaluation into large-scale simulated environments augmented with online human feedback. Leveraging advances in vision-language models, 2D-to-3D generative modeling, and differentiable rendering, our approach automatically converts video demonstrations from widely used robot datasets into simulated counterparts. Within these digital twins, we assess VLA policies using both automated vision-language-model-guided scoring and scalable human preference judgments collected from crowdworkers, transforming human involvement from tedious scene setup, resetting, and safety supervision into lightweight preference comparisons. To measure robustness, we systematically perturb simulated environments along multiple axes, including textures and object placements, stress-testing policy generalization under controlled variation. The result is a continuously evolving, reproducible, and scalable benchmark for real-world-trained robot manipulation policies, addressing a critical missing capability in today's robotics landscape.

cs.RO↗

arXiv2023

Image-based Visual Servo Control for Aerial Manipulation Using a Fully-Actuated UAV

Using Unmanned Aerial Vehicles (UAVs) to perform high-altitude manipulation tasks beyond just passive visual application can reduce the time, cost, and risk of human workers. Prior research on aerial manipulation has relied on either ground truth state estimate or GPS/total station with some Simultaneous Localization and Mapping (SLAM) algorithms, which may not be practical for many applications close to infrastructure with degraded GPS signal or featureless environments. Visual servo can avoid the need to estimate robot pose. Existing works on visual servo for aerial manipulation either address solely end-effector position control or rely on precise velocity measurement and pre-defined visual visual marker with known pattern. Furthermore, most of previous work used under-actuated UAVs, resulting in complicated mechanical and hence control design for the end-effector. This paper develops an image-based visual servo control strategy for bridge maintenance using a fully-actuated UAV. The main components are (1) a visual line detection and tracking system, (2) a hybrid impedance force and motion control system. Our approach does not rely on either robot pose/velocity estimation from an external localization system or pre-defined visual markers. The complexity of the mechanical system and controller architecture is also minimized due to the fully-actuated nature. Experiments show that the system can effectively execute motion tracking and force holding using only the visual guidance for the bridge painting. To the best of our knowledge, this is one of the first studies on aerial manipulation using visual servo that is capable of achieving both motion and force control without the need of external pose/velocity information or pre-defined visual guidance.

cs.RO↗

arXiv2021

A Generalized Kalman Filter Augmented Deep-Learning based Approach for Autonomous Landing in MAVs

Autonomous landing systems for Micro Aerial Vehicles (MAV) have been proposed using various combinations of GPS-based, vision, and fiducial tag-based schemes. Landing is a critical activity that a MAV performs and poor resolution of GPS, degraded camera images, fiducial tags not meeting required specifications and environmental factors pose challenges. An ideal solution to MAV landing should account for these challenges and for operational challenges which could cause unplanned movements and landings. Most approaches do not attempt to solve this general problem but look at restricted sub-problems with at least one well-defined parameter. In this work, we propose a generalized end-to-end landing site detection system using a two-stage training mechanism, which makes no pre-assumption about the landing site. Experimental results show that we achieve comparable accuracy and outperform existing methods for the time required for landing.

cs.RO↗