Searcharxiv⌕ Search

arXiv subjects

Georg Martius

Publications and source records attributed to Georg Martius.

At least 19 recordsLinked to original sources
arXiv2026

Lodos-v2: An Efficient Primal Formulation of the Exact Frictional Contact Problem

Lodos-v2 is a GPU-based simulation framework for massively parallel rigid-body dynamics with contact. It is specifically designed to achieve high throughput in scenes involving collisions among large numbers of detailed meshes. Its predecessor, Lodos-v1, had two main limitations. First, it solved the standard convex relaxation of cone-complementarity-based contact dynamics, thereby inheriting well-known physical artifacts, including lift-off and artificial compliance in the normal direction, as well as creep in the tangential direction. Second, its contact-group reparameterization scheme, which rescales spring-damper forces using a single factor per collision pair, could not be integrated with other constraints required by a full-fledged simulator, such as joint limits and welds. Lodos-v2 addresses both limitations through two main contributions. First, it introduces an efficient algorithm for solving the exact frictional contact problem by sequentially solving a cascade of convex relaxations in primal form within an outer proximal minimization loop. Second, it extends the contact-group reparameterization scheme of Lodos-v1 to the primal formulation of cone-complementarity-based contact dynamics, enabling its integration with the other constraints of a full-fledged simulator. Experiments demonstrate that these contributions result in throughput improvements over established rigid-body simulation frameworks. The source code is available at https://github.com/martius-lab/lodos.

cs.RO↗
arXiv2026

Lodos: A Lightweight Simulator Designed for Contact-Rich Interactions with Detailed Meshes

In recent years, massively parallelized rigid-body simulation has played a central role in robotics research, enabling rapid progress in areas such as reinforcement learning, stochastic optimal control, and randomized smoothing-based trajectory optimization. Particularly in contact-rich settings, the scalability of such simulations in large part depends on well-optimized representations of collision geometry, often requiring a coarse approximation of the underlying surfaces using primitives such as spheres, capsules, cylinders, and boxes. Whenever the complexity of the surfaces or the precision demands of the application render such approximations insufficient, it is instead necessary to employ mesh-mesh collisions, which impose a significant reduction in throughput. This paper proposes a simulation framework designed from scratch to address this bottleneck, with novel routines for broadphase and narrowphase collision detection as well as the subsequent contact dynamics computation. As experimentally validated, the framework matches existing well-established simulators in terms of physical faithfulness, and can achieve approximately an order of magnitude higher throughput in the detailed mesh-mesh collision setting that it specializes in. The source code is available at https://github.com/martius-lab/lodos.

cs.RO↗
arXiv2026

Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons

Cortical neurons are complex, multi-timescale processors wired into recurrent circuits, shaped by long evolutionary pressure under stringent biological constraints. Mainstream machine learning, by contrast, predominantly builds models from extremely simple units, a default inherited from early neural-network theory. We treat this as a normative architectural question. How should one split a fixed parameter budget $P$ between the number of units $N$, per-unit effective complexity $k_e$, and per-unit connectivity $k_c$? What controls the optimal allocation? This calls for a model in which per-unit complexity can be tuned independently of width and connectivity. Accordingly, we introduce the ELM Network, whose recurrent layer is built from Expressive Leaky Memory (ELM) neurons, chosen to mirror functional components of cortical neurons. The architecture allows for individually adjusting $N$, $k_e$, and $k_c$ and trains stably across orders of magnitude in scale. We evaluate the model on two qualitatively different sequence benchmarks: the neuromorphic SHD-Adding task and Enwik8 character-level language modeling. Performance improves monotonically along each of the three axes individually. Under a fixed budget, a clear non-trivial optimum emerges in their tradeoff, and larger budgets favor both more numerous \emph{and} more complex neurons. A closed-form information-theoretic proxy captures these tradeoffs and attributes the diminishing returns at two ends to: per-neuron signal-to-noise saturation and across-neuron redundancy. A hyperparameter sweep spanning three orders of magnitude in trainable parameters traces a near-Pareto-frontier scaling law consistent with the proxy. This suggests that the simple-unit default in ML is not obviously optimal once this tradeoff surface is probed, and offers a normative lens on cortex's reliance on complex spatio-temporal integrators.

cs.LG↗
arXiv2026

DriveMLP: When Training Strategy Outperforms Model Complexity in Autonomous Driving

Learning motion planning policies that remain reliable under closed-loop execution is a central challenge in Autonomous Driving (AD). Imitation Learning (IL) scales well to large AD datasets but suffers from distribution shift, causal confusion, and compounding errors under closed-loop execution. In contrast, Reinforcement Learning (RL) typically requires handcrafted rule-based rewards and massive simulation. We study a simple closed-loop IL framework that uses RL purely as an optimization tool, guided by a trajectory-distance reward derived from logged expert data. We refer to this training strategy as Expert-Guided RL (EGRL). Through a controlled empirical study we find evidence that the training procedure, rather than model size and complexity, accounts for a substantial part of the performance gains. We then introduce DriveMLP, a lightweight MLP policy trained with EGRL, as a simple instantiation of these findings. It achieves a score of 86.51 on the nuPlan Val14 Reactive benchmark, a +3.2 point improvement over the previous best IL planner (Flow Planner), with >15x faster inference. Code is available at: https://github.com/alessandro-canevaro/DriveMLP .

cs.LG↗
arXiv2026

Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction

The growing interest in behavior foundation models, combined with recent advancements in generative modeling, has led to an appealing recipe for reinforcement learning from unlabeled data: pre-train a generative model to model occupancies, i.e., discounted state visitations, on reward-free trajectories, such that a policy can be easily extracted once a small reward-labeled dataset becomes available. We decompose this recipe along three axes: (i) the degree to which the multi-modal structure of occupancies must be captured, (ii) the class of generative model, and (iii) the method used for policy extraction. Along each axis, we consider existing choices, propose simpler alternatives, and validate each decision experimentally. This analysis culminates in a novel, streamlined method that leverages drifting, a modern one-step generative sampler, to model the occupancy. We show that this enables policy extraction via direct differentiation through the occupancy model, and bypasses the need for critic distillation. Overall, we observe that this nimble setup leads to improvements in performance on standard benchmarks.

cs.LG↗
arXiv2026

LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors

Learning-based quadrupedal locomotion typically relies on complex reward formulations that entangle task specification, operational limits, gait preference, and terrain adaptation within a single optimization objective. We instead treat these functions through distinct mechanisms: rewards for task specification, constraints for operational limits, energy minimization for gait preference, and exteroceptive perception for adapting energy use to terrain difficulty. We show that these components jointly enable efficient, terrain-adaptive locomotion, and that removing each component exposes a distinct failure mode. Our formulation removes explicit gait priors (including air-time, contact-count, and foot-clearance targets) in favor of emergent behavior. Compared to a conventional complex-reward baseline, our formulation achieves comparable terrain traversal while reducing cost of transport by 56% and operational-limit violations by 96%. The resulting policies transfer zero-shot to a physical Unitree Go2 using LiDAR-based elevation mapping. Project website with videos: https://tinyurl.com/locomposition.

cs.RO↗
arXiv2026

VioLA: Learning Generalist Humanoid Control Policies from Human Data

Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and fingers must move together while the robot keeps its balance, which makes joint-level actions hard to learn. And humanoid demonstrations are scarce, so current humanoid generalist policies do not follow new instructions out of the box and are fine-tuned on teleoperated demonstrations of each task before deployment. Human demonstrations exist in far larger numbers, but a person's motion is not a robot command. We remove both obstacles by changing what the generalist policy predicts. We introduce VioLA, a generalist humanoid policy that predicts body and hand motion latents instead of joint commands. A pretrained body- and hand-controller execute these latents on the robot. Their corresponding motion encoders map human and robot motion into the same latent spaces. A human recording is therefore labeled in the policy's action space, and the training demonstration pool contains 140.6 million frames, 93.2% of them human. As a result, VioLA follows locomotion instructions on the real robot zero-shot, without task-specific fine-tuning, reaching 100% success where GR00T N1.7 and $Ψ_0$ reach 16.7% and 0%, respectively. It also reaches 88.6% manipulation success without task-specific fine-tuning. The same approach works across two VLA and one world-action model backbones. A generalist policy trained on human demonstrations alone performs locomotion tasks on the real robot zero-shot. Code and checkpoints will be released.

cs.RO↗
arXiv2026

Stochastic Decision Horizons for Survival-Based Constrained Reinforcement Learning

We propose stochastic decision horizons (SDH), a theoretically grounded framework for survival-based constrained reinforcement learning from per-step violation signals. Rather than treating violations as expenditure of a cumulative budget, SDH shortens the effective decision horizon when violations occur, reducing current reward credit and future bootstrapping. We show that this construction represents a geometric-horizon survival constraint and, for a fixed Lagrange multiplier, remains the same SDH problem up to a constant reward offset that acts as an implicit incentive for survival. Using control as inference, we derive two off-policy and replay-compatible, regularized algorithms with post-violation semantics. Absorbing-state ends the decision process, so only surviving decisions pay policy KL, yielding AS-SAC. Virtual termination stops reward credit while the process continues, retaining ordinary discounted KL and yielding VT-MPO. To connect SDH with cumulative-cost CMDPs, we introduce violation-depth profiles. Under exponential-tail single-scale profiles, the SDH statistic determines cumulative cost; departures from this form mark where the connection breaks. Experiments validate both the method and this predicted scope. On the 90-muscle H2190 humanoid in Hyfydy, VT-MPO matches the EWA reference in peak gait realism, with its highest observed gait-match checkpoint at 21M environment steps versus 90M for EWA and markedly more stable training. On Safety Gymnasium, violation-depth profiles predict the regimes in which SDH achieves strong reward-violation trade-offs.

cs.LG↗
arXiv2026

Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models

Learning world models from offline trajectories enables agents to accomplish different tasks through planning. Object-centric (OC) representations, which decompose a scene into a set of slots that bind to its objects, have been proposed as an inductive bias for world models that are more sample-efficient and generalize better. Yet prior object-centric world models (OCWMs) take the slot encoder as given and evaluate only in-distribution, leaving open whether the object-centric bias actually delivers for planning and what within the OCWM drives it. We conduct a controlled study of OCWMs for visual model-predictive control along two axes: object-centric representation quality and generalization under distribution shift relative to scene-centric models. We find that (i) planning success correlates positively with unsupervised slot-quality metrics (FG-ARI, mBO), though the gains saturate at high slot quality; (ii) with well-bound slots, the auxiliary proprioception inputs and masking inductive bias that prior methods relied on become unnecessary; and (iii) under unseen distribution shifts, the OCWM with well-bound slots is more robust overall than the end-to-end trained scene-centric LeWM, while DINO-WM, built on similar frozen pretrained features, remains competitive -- pointing to pretrained features as a key contributor to robustness.

cs.CV↗
arXiv2026

Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints

Offline diversity maximization under imitation constraints can transform demonstration data into a set of distinct behavioral policies, improving robustness to distribution shift without additional environment interaction. In practice, however, existing offline approaches often rely on mutual-information objectives that require training a skill discriminator and can become unstable under the non-stationary rewards induced by alternating Lagrangian optimization. We introduce Dual-Force, an offline algorithm that (i) maximizes diversity using an off-policy estimator of a Van der Waals (VdW) force objective computed from successor features, eliminating the skill discriminator, and (ii) stabilizes training under non-stationary intrinsic rewards by conditioning the value function and policy on a pre-trained Functional Reward Encoding (FRE). The FRE code also enables zero-shot recall of every encountered skill via its associated latent representation, removing the need to pre-specify a fixed number of skills. On two Solo12 simulation benchmarks (locomotion and obstacle navigation), Dual-Force recovers diverse high-performing behaviors while matching a target expert state occupancy and improves robustness in adversarial obstacle variations.

cs.LG↗
arXiv2026

Advances, challenges, and opportunities for legged robots

Humanoid and quadrupedal robots have the potential to revolutionize the way we work, interact, and coexist with intelligent machines. To understand their effects on society and how they can enable scientific discovery, we assess the current capabilities of these systems along hardware, locomotion, autonomy, data, and applications. We identify recent advances and key open challenges that must be overcome to enable widespread adoption and new use cases for legged robots. Last, we provide an outlook on the future of legged robots, exploring their ethical considerations, economic potential, policy implications, and broader societal effects.

cs.RO↗
arXiv2026

Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning

While closed-loop motion planners trained on large-scale, object-level datasets, e.g., nuPlan, demonstrate strong in-distribution (ID) performance, their generalization to novel urban topologies and recovery mechanisms following execution perturbations remain under-explored. To address this, we present Shift & Drift, a novel dual-track benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift: (1) The Semantic Shift Track leverages a novel conversion pipeline that transforms the aerial, DeepScenario Open 3D dataset into the nuPlan simulation framework. This enables zero-shot evaluation of planners trained on North American and Singaporean data against 1,182 scenarios spanning four German cities and the US city of San Francisco featuring dense pedestrian-cyclist interactions. (2) The State-Distribution Drift Track injects stochastic perturbations into the ego vehicle's dynamics to quantify robustness against compounding execution errors. Based on this, we systematically evaluate the failure modes of diverse planning paradigms under semantic and state-distribution shifts. While imitation learning methods achieve high scores in ID benchmarks, they exhibit significant failures under semantic shift, particularly in pedestrian-dense environments, and suffer from persistent drift when subjected to temporally correlated actuation noise. In contrast, the evaluated reinforcement-learning-based planner demonstrates more graceful degradation, maintaining higher safety and progress metrics across both tracks. Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous benchmark to evaluate progress toward reliable deployment.

cs.RO↗
arXiv2026

Learning 3D-Gaussian Simulators from RGB Videos

Realistic simulation is critical for applications ranging from robotics to animation. Learned simulators have emerged as a possibility to capture real world physics directly from video data, but very often require privileged information such as depth information, particle tracks and hand-engineered features to maintain spatial and temporal consistency. These strong inductive biases or ground truth 3D information help in domains where data is sparse but limit scalability and generalization in data rich regimes. To overcome the key limitations, we propose 3DGSim, a learned 3D simulator that directly learns physical interactions from multi-view RGB videos. 3DGSim unifies 3D scene reconstruction, particle dynamics prediction and video synthesis into an end-to-end trained framework. It adopts MVSplat to learn a latent particle-based representation of 3D scenes, a Point Transformer for particle dynamics, a Temporal Merging module for consistent temporal aggregation and Gaussian Splatting to produce novel view renderings. By jointly training inverse rendering and dynamics forecasting, 3DGSim embeds the physical properties into point-wise latent features. This enables the model to capture diverse physical behaviors, from rigid to elastic, cloth-like dynamics, and boundary conditions (e.g. fixed cloth corner), along with realistic lighting effects that also generalize to unseen multibody interactions and novel scene edits.

cs.GR↗
arXiv2026

Belt-Finger: An Affordable Soft Belt-Driven Gripper for Dexterous In-Hand Manipulation

Parallel-jaw grippers are the default manipulator choice in robotics because they are simple, robust, and inexpensive. Their limited in-hand mobility, however, often forces large arm motions and restricts dexterous manipulation in confined workspaces. We present a parallel-gripper upgrade: a double-soft-belt-based finger module that preserves standard opening/closing while adding three in-hand degrees of freedom (DoF): translation, pitch, and roll. The mechanism is deliberately kept simple and engineered for inexpensive manufacturing and straightforward integration, preserving the reliability and precise control of traditional parallel grippers while greatly broadening the range of manipulation capabilities. To demonstrate the utility of the added DoFs, we integrate the gripper in two control pipelines. First, we adapt a model predictive controller for in-hand manipulation of known objects. Second, we introduce a lightweight teleoperation interface that enables simultaneous control of the robot arm and gripper (10 DoFs total) with minimal hardware. Across a suite of challenging manipulation tasks executed via teleoperation, MPC, and trained policies, the proposed gripper consistently improves dexterity and task feasibility compared to a conventional parallel gripper

cs.RO↗
arXiv2026

Novel Algorithms for Smoothly Differentiable and Efficiently Vectorizable Contact Manifold Construction

Generating intelligent robot behavior in contact-rich settings is a research problem where zeroth-order methods currently prevail. Developing methods that make use of first/second order information about rigid-body dynamics in the presence of contact holds great promise in terms of increasing the solution speed and computational efficiency. The main bottleneck in this research direction is the difficulty in obtaining gradients and Hessians that are actually useful for numerical optimization, due to pathologies in all three steps of a common simulation pipeline: i) collision detection, ii) contact dynamics, iii) time integration. This abstract proposes a method that aims to address the collision detection part of the puzzle, via a novel pipeline designed from scratch with smooth (i.e. twice) differentiability and massive vectorizability on GPUs as the main priorities. This is in contrast to standard collision detection routines that are instead optimized for runtime on CPUs and minimal memory footprint, but do employ logic and control flow that hinder differentiability and vectorization. The proposed pipeline consists of the following contributions: i) highly expressive and compute efficient SDF representations, ii) differentiable broad-phase and narrow-phase routines that use these representations to generate vertex-SDF and edge-SDF contacts, iii) a differentiable routine for convex decomposition based contact blending.

cs.RO↗
arXiv2026

Test-time Offline Reinforcement Learning on Goal-related Experience

Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned reinforcement learning algorithms: a universal value function is trained on a large number of goals, and the policy is evaluated on a single goal in each test episode. Extensive research in foundation models has shown that performance can be substantially improved through test-time training, specializing the model to the current goal. We find similarly that test-time offline reinforcement learning on experience related to the test goal can lead to substantially better policies at modest compute costs. We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state and quality with respect to the evaluation goal. We demonstrate across a wide range of high-dimensional loco-navigation and manipulation tasks that fine-tuning a policy on the selected data for a few gradient steps leads to significant performance gains over standard offline pre-training. Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out. Finally, we study compute allocation at inference, demonstrating that, at comparable costs, GC-TTT induces performance gains that are not achievable by scaling model size.

cs.LG↗
arXiv2026

Drifting Fields are not Conservative

Drifting models have recently gained attention for generating high-quality samples in a single forward pass. During training, they learn a push-forward map by following a vector-valued field, the drift field. We ask whether this procedure is equivalent to optimizing a scalar loss and find that, in general, it is not: drift fields are not conservative and cannot be written as the gradient of any scalar potential. We identify the position-dependent normalization as the source of non-conservatism, with the Gaussian kernel as the unique radial exception. Guided by this, we introduce the sharp kernel $k^\#$ and a sharp-normalized drift field that is conservative for general radial kernels. The resulting vector field is the gradient of a scalar potential that can be optimized directly using stochastic gradient descent. Moreover, the field has the form of a score difference of kernel density estimates, and gives exact equilibrium identifiability. Thus, sharp normalization closes the gap to related literature, such as Wasserstein gradient-flows and denoising score matching, also for non-Gaussian kernels. Empirically, sharp normalization preserves the performance of the original drifting objective, suggesting that the non-conservative flexibility is not required for high-quality generation.

cs.LG↗
arXiv2026

Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control

Contact forces introduce discontinuities into robot dynamics that severely limit the use of simulators for gradient-based optimization. Penalty-based simulators such as MuJoCo, soften contact resolution to enable gradient computation. However, realistically simulating hard contacts requires stiff solver settings, which leads to incorrect simulator gradients when using automatic differentiation. Contrarily, using non-stiff settings strongly increases the sim-to-real gap. We analyze penalty-based simulators to pinpoint why gradients degrade under hard contacts. Building on these insights, we propose DiffMJX, which couples adaptive time integration with penalty-based simulation to substantially improve gradient accuracy. A second challenge is that contact gradients vanish when bodies separate. To address this, we introduce contacts from distance (CFD) which combines penalty-based simulation with straight-through estimation. By applying CFD exclusively in the backward pass, we obtain informative pre-contact gradients while retaining physical realism.

cs.RO↗