ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors

Learning generalizable and robust behavior cloning policies requires large volumes of high-quality robotics data. While human demonstrations (e.g., through teleoperation) serve as the standard source for expert behaviors, acquiring such data at scale in the real world is prohibitively expensive. This paper introduces ExpertGen, a framework that automates expert policy learning in simulation to enable scalable sim-to-real transfer. ExpertGen first initializes a behavior prior using a diffusion policy trained on imperfect demonstrations, which may be synthesized by large language models or provided by humans. Reinforcement learning is then used to steer this prior toward high task success by optimizing the diffusion model's initial noise while keep original policy frozen. By keeping the pretrained diffusion policy frozen, ExpertGen regularizes exploration to remain within safe, human-like behavior manifolds, while also enabling effective learning with only sparse rewards. Empirical evaluations on challenging manipulation benchmarks demonstrate that ExpertGen reliably produces high-quality expert policies with no reward engineering. On industrial assembly tasks, ExpertGen achieves a 90.5% overall success rate, while on long-horizon manipulation tasks it attains 85% overall success, outperforming all baseline methods. The resulting policies exhibit dexterous control and remain robust across diverse initial configurations and failure states. To validate sim-to-real transfer, the learned state-based expert policies are further distilled into visuomotor policies via DAgger and successfully deployed on real robotic hardware.

PPGuide: Steering Diffusion Policies with Performance Predictive Guidance

Diffusion policies have shown to be very efficient at learning complex, multi-modal behaviors for robotic manipulation. However, errors in generated action sequences can compound over time which can potentially lead to failure. Some approaches mitigate this by augmenting datasets with expert demonstrations or learning predictive world models which might be computationally expensive. We introduce Performance Predictive Guidance (PPGuide), a lightweight, classifier-based framework that steers a pre-trained diffusion policy away from failure modes at inference time. PPGuide makes use of a novel self-supervised process: it uses attention-based multiple instance learning to automatically estimate which observation-action chunks from the policy's rollouts are relevant to success or failure. We then train a performance predictor on this self-labeled data. During inference, this predictor provides a real-time gradient to guide the policy toward more robust actions. We validated our proposed PPGuide across a diverse set of tasks from the Robomimic and MimicGen benchmarks, demonstrating consistent improvements in performance.

FlowDet: Overcoming Perspective and Scale Challenges in Real-Time End-to-End Traffic Detection

End-to-end object detectors offer a promising NMS-free paradigm for real-time applications, yet their high computational cost remains a significant barrier, particularly for complex scenarios like intersection traffic monitoring. To address this challenge, we propose FlowDet, a high-speed detector featuring a decoupled encoder optimization strategy applied to the DETR architecture. Specifically, FlowDet employs a novel Geometric Deformable Unit (GDU) for traffic-aware geometric modeling and a Scale-Aware Attention (SAA) module to maintain high representational power across extreme scale variations. To rigorously evaluate the model's performance in environments with severe occlusion and high object density, we collected the Intersection-Flow-5k dataset, a new challenging scene for this task. Evaluated on Intersection-Flow-5k, FlowDet establishes a new state-of-the-art. Compared to the strong RT-DETR baseline, it improves AP(test) by 1.5% and AP50(test) by 1.6%, while simultaneously reducing GFLOPs by 63.2% and increasing inference speed by 16.2%. Our work demonstrates a new path towards building highly efficient and accurate detectors for demanding, real-world perception systems. The Intersection-Flow-5k dataset is available at https://github.com/AstronZh/Intersection-Flow-5K.

Dynamic Robot Tool Use with Vision Language Models

Tool use enhances a robot's task capabilities. Recent advances in vision-language models (VLMs) have equipped robots with sophisticated cognitive capabilities for tool-use applications. However, existing methodologies focus on elementary quasi-static tool manipulations or high-level tool selection while neglecting the critical aspect of task-appropriate tool grasping. To address this limitation, we introduce inverse Tool-Use Planning (iTUP), a novel VLM-driven framework that enables grounded fine-grained planning for versatile robotic tool use. Through an integrated pipeline of VLM-based tool and contact point grounding, position-velocity trajectory planning, and physics-informed grasp generation and selection, iTUP demonstrates versatility across (1) quasi-static and more challenging (2) dynamic and (3) cluster tool-use tasks. To ensure robust planning, our framework integrates stable and safe task-aware grasping by reasoning over semantic affordances and physical constraints. We evaluate iTUP and baselines on a comprehensive range of realistic tool use tasks including precision hammering, object scooping, and cluster sweeping. Experimental results demonstrate that iTUP ensures a thorough grounding of cognition and planning for challenging robot tool use across diverse environments.

Implicit Physics-aware Policy for Dynamic Manipulation of Rigid Objects via Soft Body Tools

Recent advancements in robot tool use have unlocked their usage for novel tasks, yet the predominant focus is on rigid-body tools, while the investigation of soft-body tools and their dynamic interaction with rigid bodies remains unexplored. This paper takes a pioneering step towards dynamic one-shot soft tool use for manipulating rigid objects, a challenging problem posed by complex interactions and unobservable physical properties. To address these problems, we propose the Implicit Physics-aware (IPA) policy, designed to facilitate effective soft tool use across various environmental configurations. The IPA policy conducts system identification to implicitly identify physics information and predict goal-conditioned, one-shot actions accordingly. We validate our approach through a challenging task, i.e., transporting rigid objects using soft tools such as ropes to distant target positions in a single attempt under unknown environment physics parameters. Our experimental results indicate the effectiveness of our method in efficiently identifying physical properties, accurately predicting actions, and smoothly generalizing to real-world environments. The related video is available at: https://youtu.be/4hPrUDTc4Rg?si=WUZrT2vjLMt8qRWA

Passive iFIR filters for data-driven control

We consider the design of a new class of passive iFIR controllers given by the parallel action of an integrator and a finite impulse response filter. iFIRs are more expressive than PID controllers but retain their features and simplicity. The paper provides a model-free data-driven design for passive iFIR controllers based on virtual reference feedback tuning. Passivity is enforced through constrained optimization (three different formulations are discussed). The proposed design does not rely on large datasets or accurate plant models.

DeRi-IGP: Manipulating Rigid Objects Using Deformable Objects via Iterative Grasp-Pull

Heterogeneous systems manipulation, i.e., manipulating rigid objects via deformable (soft) objects, is an emerging field that remains in its early stages of research. Existing works in this field suffer from limited action and operational space, poor generalization ability, and expensive development. To address these challenges, we propose a universally applicable and effective moving primitive, Iterative Grasp-Pull (IGP), and a sample-based framework, DeRi-IGP, to solve the heterogeneous system manipulation task. The DeRi-IGP framework uses local onboard robots' RGBD sensors to observe the environment, comprising a soft-rigid body system. It then uses this information to iteratively grasp and pull a soft body (e.g., rope) to move the attached rigid body to a desired location. We evaluate the effectiveness of our framework in solving various heterogeneous manipulation tasks and compare its performance with several state-of-the-art baselines. The result shows that DeRi-IGP outperforms other methods by a significant margin. In addition, we also demonstrate the advantage of the large operational space of IGP in the long-distance object acquisition task within both simulated and real environments.

AnyPose: Anytime 3D Human Pose Forecasting via Neural Ordinary Differential Equations

Anytime 3D human pose forecasting is crucial to synchronous real-world human-machine interaction, where the term ``anytime" corresponds to predicting human pose at any real-valued time step. However, to the best of our knowledge, all the existing methods in human pose forecasting perform predictions at preset, discrete time intervals. Therefore, we introduce AnyPose, a lightweight continuous-time neural architecture that models human behavior dynamics with neural ordinary differential equations. We validate our framework on the Human3.6M, AMASS, and 3DPW dataset and conduct a series of comprehensive analyses towards comparison with existing methods and the intersection of human pose and neural ordinary differential equations. Our results demonstrate that AnyPose exhibits high-performance accuracy in predicting future poses and takes significantly lower computational time than traditional methods in solving anytime prediction tasks.

Efficient Q-Learning over Visit Frequency Maps for Multi-agent Exploration of Unknown Environments

The robot exploration task has been widely studied with applications spanning from novel environment mapping to item delivery. For some time-critical tasks, such as rescue catastrophes, the agent is required to explore as efficiently as possible. Recently, Visit Frequency-based map representation achieved great success in such scenarios by discouraging repetitive visits with a frequency-based penalty. However, its relatively large size and single-agent settings hinder its further development. In this context, we propose Integrated Visit Frequency Map, which encodes identical information as Visit Frequency Map with a more compact size, and a visit frequency-based multi-agent information exchange and control scheme that is able to accommodate both representations. Through tests in diverse settings, the results indicate our proposed methods can achieve a comparable level of performance of VFM with lower bandwidth requirements and generalize well to different multi-agent setups including real-world environments.

DeRi-Bot: Learning to Collaboratively Manipulate Rigid Objects via Deformable Objects

Recent research efforts have yielded significant advancements in manipulating objects under homogeneous settings where the robot is required to either manipulate rigid or deformable (soft) objects. However, the manipulation under heterogeneous setups that involve both deformable and rigid objects remains an unexplored area of research. Such setups are common in various scenarios that involve the transportation of heavy objects via ropes, e.g., on factory floors, at disaster sites, and in forestry. To address this challenge, we introduce DeRi-Bot, the first framework that enables the collaborative manipulation of rigid objects with deformable objects. Our framework comprises an Action Prediction Network (APN) and a Configuration Prediction Network (CPN) to model the complex pattern and stochasticity of soft-rigid body systems. We demonstrate the effectiveness of DeRi-Bot in moving rigid objects to a target position with ropes connected to robotic arms. Furthermore, DeRi-Bot is a distributive method that can accommodate an arbitrary number of robots or human partners without reconfiguration or retraining. We evaluate our framework in both simulated and real-world environments and show that it achieves promising results with strong generalization across different types of objects and multi-agent settings, including human-robot collaboration.