Capsizing-Guided Trajectory Optimization for Autonomous Navigation with Rough Terrain

It is a challenging task for ground robots to autonomously navigate in harsh environments due to the presence of non-trivial obstacles and uneven terrain. This requires trajectory planning that balances safety and efficiency. The primary challenge is to generate a feasible trajectory that prevents robot from tip-over while ensuring effective navigation. In this paper, we propose a capsizing-aware trajectory planner (CAP) to achieve trajectory planning on the uneven terrain. The tip-over stability of the robot on rough terrain is analyzed. Based on the tip-over stability, we define the traversable orientation, which indicates the safe range of robot orientations. This orientation is then incorporated into a capsizing-safety constraint for trajectory optimization. We employ a graph-based solver to compute a robust and feasible trajectory while adhering to the capsizing-safety constraint. Extensive simulation and real-world experiments validate the effectiveness and robustness of the proposed method. The results demonstrate that CAP outperforms existing state-of-the-art approaches, providing enhanced navigation performance on uneven terrains.

Learning an Implicit Physics Model for Image-based Fluid Simulation

Humans possess an exceptional ability to imagine 4D scenes, encompassing both motion and 3D geometry, from a single still image. This ability is rooted in our accumulated observations of similar scenes and an intuitive understanding of physics. In this paper, we aim to replicate this capacity in neural networks, specifically focusing on natural fluid imagery. Existing methods for this task typically employ simplistic 2D motion estimators to animate the image, leading to motion predictions that often defy physical principles, resulting in unrealistic animations. Our approach introduces a novel method for generating 4D scenes with physics-consistent animation from a single image. We propose the use of a physics-informed neural network that predicts motion for each surface point, guided by a loss term derived from fundamental physical principles, including the Navier-Stokes equations. To capture appearance, we predict feature-based 3D Gaussians from the input image and its estimated depth, which are then animated using the predicted motions and rendered from any desired camera perspective. Experimental results highlight the effectiveness of our method in producing physically plausible animations, showcasing significant performance improvements over existing methods. Our project page is https://physfluid.github.io/ .

DiSC-Med: Diffusion-based Semantic Communications for Robust Medical Image Transmission

The rapid development of artificial intelligence has driven smart health with next-generation wireless communication technologies, stimulating exciting applications in remote diagnosis and intervention. To enable a timely and effective response for remote healthcare, efficient transmission of medical data through noisy channels with limited bandwidth emerges as a critical challenge. In this work, we propose a novel diffusion-based semantic communication framework, namely DiSC-Med, for the medical image transmission, where medical-enhanced compression and denoising blocks are developed for bandwidth efficiency and robustness, respectively. Unlike conventional pixel-wise communication framework, our proposed DiSC-Med is able to capture the key semantic information and achieve superior reconstruction performance with ultra-high bandwidth efficiency against noisy channels. Extensive experiments on real-world medical datasets validate the effectiveness of our framework, demonstrating its potential for robust and efficient telehealth applications.

Generalized Advantage Estimation for Distributional Policy Gradients

Generalized Advantage Estimation (GAE) has been used to mitigate the computational complexity of reinforcement learning (RL) by employing an exponentially weighted estimation of the advantage function to reduce the variance in policy gradient estimates. Despite its effectiveness, GAE is not designed to handle value distributions integral to distributional RL, which can capture the inherent stochasticity in systems and is hence more robust to system noises. To address this gap, we propose a novel approach that utilizes the optimal transport theory to introduce a Wasserstein-like directional metric, which measures both the distance and the directional discrepancies between probability distributions. Using the exponentially weighted estimation, we leverage this Wasserstein-like directional metric to derive distributional GAE (DGAE). Similar to traditional GAE, our proposed DGAE provides a low-variance advantage estimate with controlled bias, making it well-suited for policy gradient algorithms that rely on advantage estimation for policy updates. We integrated DGAE into three different policy gradient methods. Algorithms were evaluated across various OpenAI Gym environments and compared with the baselines with traditional GAE to assess the performance.

Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation

Depth estimation is a fundamental task in 3D computer vision, crucial for applications such as 3D reconstruction, free-viewpoint rendering, robotics, autonomous driving, and AR/VR technologies. Traditional methods relying on hardware sensors like LiDAR are often limited by high costs, low resolution, and environmental sensitivity, limiting their applicability in real-world scenarios. Recent advances in vision-based methods offer a promising alternative, yet they face challenges in generalization and stability due to either the low-capacity model architectures or the reliance on domain-specific and small-scale datasets. The emergence of scaling laws and foundation models in other domains has inspired the development of "depth foundation models": deep neural networks trained on large datasets with strong zero-shot generalization capabilities. This paper surveys the evolution of deep learning architectures and paradigms for depth estimation across the monocular, stereo, multi-view, and monocular video settings. We explore the potential of these models to address existing challenges and provide a comprehensive overview of large-scale datasets that can facilitate their development. By identifying key architectures and training strategies, we aim to highlight the path towards robust depth foundation models, offering insights into their future research and applications.

Martian World Models: Controllable Video Synthesis with Physically Accurate 3D Reconstructions

Synthesizing realistic Martian landscape videos is crucial for mission rehearsal and robotic simulation. However, this task poses unique challenges due to the scarcity of high-quality Martian data and the significant domain gap between Martian and terrestrial imagery. To address these challenges, we propose a holistic solution composed of two key components: 1) A data curation pipeline Multimodal Mars Synthesis (M3arsSynth), which reconstructs 3D Martian environments from real stereo navigation images, sourced from NASA's Planetary Data System (PDS), and renders high-fidelity multiview 3D video sequences. 2) A Martian terrain video generator, MarsGen, which synthesizes novel videos visually realistic and geometrically consistent with the 3D structure encoded in the data. Our M3arsSynth engine spans a wide range of Martian terrains and acquisition dates, enabling the generation of physically accurate 3D surface models at metric-scale resolution. MarsGen, fine-tuned on M3arsSynth data, synthesizes videos conditioned on an initial image frame and, optionally, camera trajectories or textual prompts, allowing for video generation in novel environments. Experimental results show that our approach outperforms video synthesis models trained on terrestrial datasets, achieving superior visual fidelity and 3D structural consistency.

Real-time Terrain Analysis for Off-road Autonomous Vehicles

This research addresses critical autonomous vehicle control challenges arising from road roughness variation, which induces course deviations and potential loss of road contact during steering operations. We present a novel real-time road roughness estimation system employing Bayesian calibration methodology that processes axle accelerations to predict terrain roughness with quantifiable confidence measures. The technical framework integrates a Gaussian process surrogate model with a simulated half-vehicle model, systematically processing vehicle velocity and road surface roughness parameters to generate corresponding axle acceleration responses. The Bayesian calibration routine performs inverse estimation of road roughness from observed accelerations and velocities, yielding posterior distributions that quantify prediction uncertainty for adaptive risk management. Training data generation utilizes Latin Hypercube sampling across comprehensive velocity and roughness parameter spaces, while the calibrated model integrates seamlessly with a Simplex controller architecture to dynamically adjust velocity limits based on real-time roughness predictions. Experimental validation on stochastically generated surfaces featuring varying roughness regions demonstrates robust real-time characterization capabilities, with the integrated Simplex control strategy effectively enhancing autonomous vehicle operational safety through proactive surface condition response. This innovative Bayesian framework establishes a comprehensive foundation for mitigating roughness-related operational risks while simultaneously improving efficiency and safety margins in autonomous vehicle systems.

The MOTIF Hand: A Robotic Hand for Multimodal Observations with Thermal, Inertial, and Force Sensors

Advancing dexterous manipulation with multi-fingered robotic hands requires rich sensory capabilities, while existing designs lack onboard thermal and torque sensing. In this work, we propose the MOTIF hand, a novel multimodal and versatile robotic hand that extends the LEAP hand by integrating: (i) dense tactile information across the fingers, (ii) a depth sensor, (iii) a thermal camera, (iv), IMU sensors, and (v) a visual sensor. The MOTIF hand is designed to be relatively low-cost (under 4000 USD) and easily reproducible. We validate our hand design through experiments that leverage its multimodal sensing for two representative tasks. First, we integrate thermal sensing into 3D reconstruction to guide temperature-aware, safe grasping. Second, we show how our hand can distinguish objects with identical appearance but different masses - a capability beyond methods that use vision only.

SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending

Humanoid robots hold significant potential in accomplishing daily tasks across diverse environments thanks to their flexibility and human-like morphology. Recent works have made significant progress in humanoid whole-body control and loco-manipulation leveraging optimal control or reinforcement learning. However, these methods require tedious task-specific tuning for each task to achieve satisfactory behaviors, limiting their versatility and scalability to diverse tasks in daily scenarios. To that end, we introduce SkillBlender, a novel hierarchical reinforcement learning framework for versatile humanoid loco-manipulation. SkillBlender first pretrains goal-conditioned task-agnostic primitive skills, and then dynamically blends these skills to accomplish complex loco-manipulation tasks with minimal task-specific reward engineering. We also introduce SkillBench, a parallel, cross-embodiment, and diverse simulated benchmark containing three embodiments, four primitive skills, and eight challenging loco-manipulation tasks, accompanied by a set of scientific evaluation metrics balancing accuracy and feasibility. Extensive simulated experiments show that our method significantly outperforms all baselines, while naturally regularizing behaviors to avoid reward hacking, resulting in more accurate and feasible movements for diverse loco-manipulation tasks in our daily scenarios. Our code and benchmark will be open-sourced to the community to facilitate future research. Project page: https://usc-gvl.github.io/SkillBlender-web/.

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

Recent advancements in large language models (LLMs) have demonstrated impressive chain-of-thought reasoning capabilities, with reinforcement learning (RL) playing a crucial role in this progress. While "aha moment" patterns--where models exhibit self-correction through reflection--are often attributed to emergent properties from RL, we first demonstrate that these patterns exist in multimodal LLMs (MLLMs) prior to RL training but may not necessarily correlate with improved reasoning performance. Building on these insights, we present a comprehensive study on enhancing multimodal reasoning through a two-stage approach: (1) supervised fine-tuning (SFT) as a cold start with structured chain-of-thought reasoning patterns, followed by (2) reinforcement learning via GRPO to further refine these capabilities. Our extensive experiments show that this combined approach consistently outperforms both SFT-only and RL-only methods across challenging multimodal reasoning benchmarks. The resulting models achieve state-of-the-art performance among open-source MLLMs at both 3B and 7B scales, with our 7B model showing substantial improvements over base models (e.g., 66.3 %$\rightarrow$73.4 % on MathVista, 62.9 %$\rightarrow$70.4 % on We-Math) and our 3B model achieving performance competitive with several 7B models. Overall, this work provides practical guidance for building advanced multimodal reasoning models. Our code is available at https://github.com/waltonfuture/RL-with-Cold-Start.