Collision-free navigation in dynamic environments, especially with moving pedestrians, is crucial for mobile robots. This paper introduces DUNE, a depth-based policy trained in simulation for collision-free navigation of Ackermann mobile robots in unstructured indoor environments. DUNE uses a CNN-LSTM to encode depth vision and past actions, while an actor-critic network controls velocity and steering. Additionally, a depth filter bridges the sim-to-real gap. Unlike prior works relying on LIDAR and complex algorithms, DUNE achieves state-of-the-art performance with only egocentric depth perception and lightweight neural networks, both in simulation and real-world tasks.

Nonprehensile manipulation is crucial for handling objects that are too thin, large, or otherwise ungraspable in unstructured environments. While conventional planning-based approaches struggle with complex contact modeling, learning-based methods have recently emerged as a promising alternative. However, existing learning-based approaches face two major limitations: they heavily rely on multi-view cameras and precise pose tracking, and they fail to generalize across varying physical conditions, such as changes in object mass and table friction. To address these challenges, we propose the Dynamics-Adaptive World Action Model (DyWA), a novel framework that enhances action learning by jointly predicting future states while adapting to dynamics variations based on historical trajectories. By unifying the modeling of geometry, state, physics, and robot actions, DyWA enables more robust policy learning under partial observability. Compared to baselines, our method improves the success rate by 31.5% using only single-view point cloud observations in the simulation. Furthermore, DyWA achieves an average success rate of 68% in real-world experiments, demonstrating its ability to generalize across diverse object geometries, adapt to varying table friction, and robustness in challenging scenarios such as half-filled water bottles and slippery surfaces.

Legged robots with advanced manipulation capabilities have the potential to significantly improve household duties and urban maintenance. Despite considerable progress in developing robust locomotion and precise manipulation methods, seamlessly integrating these into cohesive whole-body control for real-world applications remains challenging. In this paper, we present a modular framework for robust and generalizable whole-body loco-manipulation controller based on a single arm-mounted camera. By using reinforcement learning (RL), we enable a robust low-level policy for command execution over 5 dimensions (5D) and a grasp-aware high-level policy guided by a novel metric, Generalized Oriented Reachability Map (GORM). The proposed system achieves state-of-the-art one-time grasping accuracy of 89% in real world, including challenging tasks such as grasping transparent objects. Through extensive simulations and real-world experiments, we demonstrate that our system can effectively manage a large workspace, from floor level to above body height, and perform diverse whole-body loco-manipulation tasks. See our robot at work: quadwbg.github.io.

Mobile manipulation constitutes a fundamental task for robotic assistants and garners significant attention within the robotics community. A critical challenge inherent in mobile manipulation is the effective observation of the target while approaching it for grasping. In this work, we propose a graspability-aware mobile manipulation approach powered by an online grasping pose fusion framework that enables a temporally consistent grasping observation. Specifically, the predicted grasping poses are online organized to eliminate the redundant, outlier grasping poses, which can be encoded as a grasping pose observation state for reinforcement learning. Moreover, on-the-fly fusing the grasping poses enables a direct assessment of graspability, encompassing both the quantity and quality of grasping poses. This assessment can subsequently serve as an observe-to-grasp reward, motivating the agent to prioritize actions that yield detailed observations while approaching the target object for grasping. Through extensive experiments conducted on the Habitat and Isaac Gym simulators, we find that our method attains a good balance between observation and manipulation, yielding high performance under various grasping metrics. Furthermore, we discover that the incorporation of temporal information from grasping poses aids in mitigating the sim-to-real gap, leading to robust performance in challenging real-world experiments. Project page: https://pku-epic.github.io/GAMMA/

The field of computer vision is currently transitioning from closed-set to open-set tasks. Vision foundation models have already demonstrated success in open-set scenarios. Building on these models, the utilization of a feature supervision framework can further enhance results. Our paper introduces a new method called SAMS (Segment Anything Model using Similar Images), which is a type of feature supervision framework. It is designed to segment specific masks from visual supervision features. Our framework comprises a pre-trained segmentation model and an efficient, novel prompt generation model capable of generating new prompts based on pre-extracted image features. This innovation eliminates the need for manually crafted prompts in the mask generation phase by integrating the principles of one-shot or few-shot learning with visual instructions from similar images. The effectiveness of the SAMS method is evident in its performance across various tasks, particularly in open-set tasks where traditional models tend to struggle. The pretrained model not only achieves impressive mean Intersection over Union (mIOU) scores without incurring additional time loss, but also demonstrates potential for further improvement through targeted module training.

The integration of large-scale Vision-Language Models (VLMs) with embodied AI can greatly enhance the generalizability and the capacity to follow open instructions for robots. However, existing studies on object manipulation are not up to full consideration of the 6-DoF requirements, let alone establishing a comprehensive benchmark. In this paper, we propel the pioneer construction of the benchmark and approach for Open-instruction 6-DoF Object Rearrangement (Open6DOR). Specifically, we collect a synthetic dataset of 200+ objects and carefully design 5400+ Open6DOR tasks. These tasks are divided into the Position-track, Rotation-track, and 6-DoF-track for evaluating different embodied agents in predicting the positions and rotations of target objects.Besides, we also propose a VLM-based approach for Open6DOR, named Open6DOR-GPT, which empowers GPT-4V with 3D-awareness and simulation-assistance while exploiting its strengths in generalizability and instruction-following. We compare the existing embodied agents with our Open6DOR-GPT on the proposed Open6DOR benchmark and find that Open6DOR-GPT achieves the state-of-the-art performance. We further show the impressive performance of Open6DOR-GPT in diverse real-world experiments.