IROS 2024 论文列表

Walk2Map has emerged as a promising data-driven method to generate indoor traversability maps based solely on pedestrian trajectories, offering great potential for indoor robot navigation. In this study, we investigate a novel approach called Walk2Map++, which involves replacing Walk2Map’s first-person sensor (i.e., IMU) with a human observing third-person view from the robot’s onboard camera. However, human observation from a third-person camera is significantly ill-posed due to visual uncertainties resulting from occlusion, nonlinear perspective, depth ambiguity, and human-to-human interaction. To regularize the ill-posedness, we propose integrating two types of constraints: photometric (i.e., occlusion ordering) and physical (i.e., collision avoidance). We demonstrate that these constraints can be effectively inferred from the interaction between past and present observations, human trackers, and object reconstructions. We depict the seamless integration of asynchronous map optimization events, like loop closure, into the real-time traversability map, facilitating incremental and efficient map refinement. We validate the efficacy of our enhanced methodology through rigorous fusion and comparison with established techniques, demonstrating its capability to advance traversability prediction in complex indoor environments. The code and datasets associated with this study are available for further research and adoption in the field at https://github.com/jonathantyl97/HO3-SLAM.

If a picture paints a thousand words, sound may voice a million. While recent robotic painting and image synthesis methods have achieved progress in generating visuals from text inputs, the translation of sound into images is vastly unexplored. Generally, sound-based interfaces and sonic interactions have the potential to expand accessibility and control for the user and provide a means to convey complex emotions and the dynamic aspects of the real world. In this paper, we propose an approach for using sound and speech to guide a robotic painting process, known here as robot synesthesia. For general sound, we encode the simulated paintings and input sounds into the same latent space. For speech, we decouple speech audio into its transcribed text and the tone of the speech. Whereas we use the text to control the content, we estimate the emotions from the tone to guide the mood of the painting. Our approach has been fully integrated with FRIDA, a robotic painting framework, adding sound and speech to FRIDA’s existing input modalities such as text and style. In two surveys, participants were able to correctly guess the emotion or natural sound used to generate a given painting more than twice as likely as random chance. On our sound-guided image manipulation and music-guided paintings, we discuss the results qualitatively.

Robot swarms hold immense potential for performing complex tasks far beyond the capabilities of individual robots. However, the challenge in unleashing this potential is the robots’ limited sensory capabilities, which hinder their ability to detect and adapt to unknown obstacles in real-time. To overcome this limitation, we introduce a novel robot swarm control method with an indirect obstacle detector using a smoothed particle hydrodynamics (SPH) model. The indirect obstacle detector can predict the collision with an obstacle and its collision point solely from the robot’s velocity information. This approach enables the swarm to effectively and accurately navigate environments without the need for explicit obstacle detection, significantly enhancing their operational robustness and efficiency. Our method’s superiority is quantitatively validated through a comparative analysis, showcasing its significant navigation and pattern formation improvements under obstacle-unaware conditions.

Diffusion models have marked a significant mile-stone in the enhancement of image and video generation technologies. However, generating videos that precisely retain the shape and location of moving objects such as robots remains a challenge. This paper presents diffusion models specifically tailored to generate videos that accurately maintain the shape and location of mobile robots. The proposed models incorporate techniques such as embedding accessible robot pose information and applying semantic mask regulation within the scalable and efficient ConvNext backbone network. These techniques are designed to refine intermediate outputs, therefore improving the retention performance of shape and location. Through extensive experimentation, our models have demonstrated notable improvements in maintaining the shape and location of different robots, as well as enhancing overall video generation quality, compared to the benchmark diffusion model. Codes will be open-sourced at: https://github.com/PengPaulWang/diffusion-robots.

We present a viewpoint-based non-linear Model Predictive Control (MPC) for evacuation guiding robots. Specifically, the proposed MPC algorithm enables evacuation guiding robots to track and guide cooperative human targets in emergency scenarios. Our algorithm accounts for the environment layout as well as distances between the robot and human target and distance to the goal location. A key challenge for evacuation guiding robot is the trade-off between its planned motion for leading the target toward a goal position and staying in the target’s viewpoint while maintaining line-of-sight for guiding. We illustrate the effectiveness of our proposed evacuation guiding algorithm in both simulated and real-world environments with an Unmanned Aerial Vehicle (UAV) guiding a human. Our results suggest that using the contextual information from the environment for motion planning, increases the visibility of the guiding UAV to the human while achieving faster total evacuation time.

It has been a popular trend in AI to pretrain foundation models on massive data. However, collecting sufficient offline training trajectories for robot learning is particularly expensive since valid control actions are required. Therefore, most existing robotic datasets are collected from human experts. We tackle such a data collection issue with a new framework called "robot self-teaching", which asks the robot to self-generate effective training data instead of relying on human demonstrators. Our key idea is to train a separate data-generation policy operating on the state space to automatically generate meaningful actions and trajectories with ever-growing complexities. Then, these generated data can be further used to train a visual policy with strong compositional generalization capabilities. We validate our framework in two visual manipulation testbeds, including a multi-object stacking domain and a popular RL benchmark "Franka kitchen". Experiments show that the final visual policy trained on self-generated data can accomplish novel testing goals that require long-horizon robot executions. Project website https://sites.google.com/view/robot-self-teaching.

Robots generally have a structure that combines rotational joints and links in a serial fashion. On the other hand, various joint mechanisms are being utilized in practice, such as prismatic joints, closed links, and wire-driven systems. Previous research have focused on individual mechanisms, proposing methods to design robots capable of achieving given tasks by optimizing the length of links and the arrangement of the joints. In this study, we propose a method for the design optimization of robots that combine different types of joints, specifically rotational and prismatic joints. The objective is to automatically generate a robot that minimizes the number of joints and link lengths while accomplishing a desired task, by utilizing a black-box multi-objective optimization approach. This enables the simultaneous observation of a diverse range of body designs through the obtained Pareto solutions. Our findings confirm the emergence of practical and known combinations of rotational and prismatic joints, as well as the discovery of novel joint combinations.

Reliable and robust navigation of autonomous mobile robots in indoor environments faces significant challenges due to the absence of GPS, visual degradation, repetitive structures, illumination variations, and low texture. These factors adversely affect localization systems. Current robots often use a uniform navigation approach, regardless of the varying localization uncertainties within different indoor environments. In this paper, we propose a holistic, active vision-based path planning method that produces efficient trajectories, aiming to minimize localization error and enhance navigation performance. Specifically, we utilize a 3D model of an indoor environment to derive an Artificial Potential Field (APF) with its associated localizability scores that encapsulate both visual features’ richness and fiducial markers’ placement. APF is employed to direct a Kinematically Constrained Bi-directional Rapidly Exploring Random Tree (KB-RRT) planner towards the calculation of optimal paths, prioritizing high localization areas. Subsequently, we use an online weight-adaptive MPC-based approach that, apart from robust path planning and obstacle avoidance, guides the robot towards areas with the most robust visual features in order to further refine the localization error. The proposed framework has been extensively tested in both simulation and real-world experiments with a mobile robot in a visually challenging indoor environment.

The ubiquitous deployment of robots across diverse domains, from industrial automation to personal care, underscores their critical role in modern society. However, this growing dependence has also revealed security vulnerabilities. An attack vector involves the deployment of malicious software (malware) on robots, which can cause harm to robots themselves, users, and even the surrounding environment. Machine learning approaches, particularly supervised ones, have shown promise in malware detection by building intricate models to identify known malicious code patterns. However, these methods are inherently limited in detecting unseen or zero-day malware variants as they require regularly updated massive datasets that might be unavailable to robots. To address this challenge, we introduce RoboGuardZ, a novel malware detection framework based on zero-shot learning for robots. This approach allows RoboGuardZ to identify unseen malware by establishing relationships between known malicious code and benign behaviors, allowing detection even before the code executes on the robot. To ensure practical deployment in resource-constrained robotic hardware, we employ a unique parallel structured pruning and quantization strategy that compresses the RoboGuardZ detection model by 37.4% while maintaining its accuracy. This strategy reduces the size of the model and computational demands, making it suitable for real-world robotic systems. We evaluated RoboGuardZ on a recent dataset containing real-world binary executables from multi-sensor autonomous car controllers. The framework was deployed on two popular robot embedded hardware platforms. Our results demonstrate an average detection accuracy of 94.25% and a low false negative rate of 5.8% with a minimal latency of 20 ms, which demonstrates its effectiveness and practicality.

Zero-day vulnerabilities pose a significant challenge to robot cyber-physical systems (CPS). Attackers can exploit software vulnerabilities in widely-used robotics software, such as the Robot Operating System (ROS), to manipulate robot behavior, compromising both safety and operational effectiveness. The hidden nature of these vulnerabilities requires strong defense mechanisms to guarantee the safety and dependability of robotic systems. In this paper, we introduce RoboCop, a cyber-physical attack detection framework designed to protect robots from zero-day threats. RoboCop leverages static software features in the pre-execution analysis along with runtime state monitoring to identify attack patterns and deviations that signal attacks, thus ensuring the robot’s operational integrity. We evaluated RoboCop on the F1-tenth autonomous car platform. It achieves a 93% detection accuracy against a variety of zero-day attacks targeting sensors, actuators, and controller logic. Importantly, in on-robot deployments, it identifies attacks in less than 7 seconds with a 12% computational overhead.

Autonomous Mobile Robots are used with increasing frequency in inspection and maintenance tasks completing fixed goal sequences. The downtime robots experience between goals offers an opportunity to gather additional environment information instead of resting. Uncertainty in the amount of downtime available rules out the definition of a pre-determined schedule set by an external operator. Instead, the robot itself should decide dynamically, what information it should gather before its next task begins. This results in a multi-objective optimization problem trying to maximize information gain while utilizing as much of the available time as possible. We propose a genetic algorithm to solve the presented optimization problem and introduce two different models for artificial curiosity used inside the fitness function for gathering as much information as possible. For planning the genetic algorithm utilizes a multi-map approach using information and obstacle maps. We evaluated our models in a pre-defined and pre-mapped Gazebo environment with a given information map and evaluated their performance against an information-agnostic coverage algorithm. In this work, we show that utilizing artificial curiosity in path planning can result in major information gains by effectively using downtime.

This paper aims to improve the computational efficiency of motion planning for mobile robots with non-trivial dynamics through the use of learned controllers. Offline, a system-specific controller is first trained in an empty environment. Then, for the target environment, the approach constructs a data structure, a "Roadmap with Gaps," to approximately learn how to solve planning queries using the learned controller. The roadmap nodes correspond to local regions. Edges correspond to applications of the learned controller that approximately connect these regions. Gaps arise as the controller does not perfectly connect pairs of individual states along edges. Online, given a query, a tree sampling-based motion planner uses the roadmap so that the tree’s expansion is informed towards the goal region. The tree expansion selects local subgoals given a wavefront on the roadmap that guides towards the goal. When the controller cannot reach a subgoal region, the planner resorts to random exploration to maintain probabilistic completeness and asymptotic optimality. The accompanying experimental evaluation shows that the approach significantly improves the computational efficiency of motion planning on various benchmarks, including physics-based vehicular models on uneven and varying friction terrains as well as a quadrotor under air pressure effects. Website: https://prx-kinodynamic.github.io/projects/rogue

Swarm robotics has garnered significant attention due to its ability to accomplish elaborate and synchronized tasks. Existing methodologies for motion planning of swarm robotic systems mainly encounter difficulties in scalability and safety guarantee. To address these limitations, we propose a Risk-aware swarm mOtion planner using conditional ValuE-at-Risk (ROVER) that systematically navigates large-scale swarms through cluttered environments while ensuring safety. ROVER formulates a finite-time model predictive control (FTMPC) problem predicated upon the macroscopic state of the robot swarm represented by a Gaussian Mixture Model (GMM) and integrates conditional value-at-risk (CVaR) to ensure collision avoidance. The key component of ROVER is imposing a CVaR constraint on the distribution of the Signed Distance Function between the swarm GMM and obstacles in the FTMPC to enforce collision avoidance. Utilizing the analytical expression of CVaR of a GMM derived in this work, we develop a computationally efficient solution to solve the non-linear constrained FTMPC through sequential linear programming. Simulations and comparisons with representative benchmark approaches demonstrate the effectiveness of ROVER in flexibility, scalability, and safety guarantee.

Autonomous Underwater Vehicles (AUVs) need to operate for days without human intervention and thus must be able to do efficient and reliable task planning. Unfortunately, efficient task planning requires deliberately abstract domain models (for scalability reasons), which in practice leads to plans that might be unreliable or under performing in practice. An optimal abstract plan may turn out suboptimal or unreliable during physical execution. To overcome this, we introduce a method that first generates a selection of diverse high-level plans and then assesses them in a low-level simulation to select the optimal and most reliable candidate. We evaluate the method using a realistic underwater robot simulation, estimating the risk metrics for different scenarios, demonstrating feasibility and effectiveness of the approach.

We introduce Riemannian Flow Matching Policies (RFMP), a novel model for learning and synthesizing robot visuomotor policies. RFMP leverages the efficient training and inference capabilities of flow matching methods. By design, RFMP inherits the strengths of flow matching: the ability to encode high-dimensional multimodal distributions, commonly encountered in robotic tasks, and a very simple and fast inference process. We demonstrate the applicability of RFMP to both state-based and vision-conditioned robot motion policies. Notably, as the robot state resides on a Riemannian manifold, RFMP inherently incorporates geometric awareness, which is crucial for realistic robotic tasks. To evaluate RFMP, we conduct two proof-of-concept experiments, comparing its performance against Diffusion Policies. Although both approaches successfully learn the considered tasks, our results show that RFMP provides smoother action trajectories with significantly lower inference times.

In this paper, we focus on improving planning efficiency for ground vehicles in navigation and exploration tasks where the environment is unknown or partially known, leading to frequent updates of the navigational goal as new sensory information is acquired. Asymptotically optimal motion planners like RRT* or FMT* can be used to plan the sequence of actions the robot can follow to achieve its current goal. Frequent replanning of the whole action sequence becomes computationally demanding when actions are not executed precisely because of limited information about the foreground terrain. The decoupled approach can decrease the computational burden with separated path planning and path following; however, it might lead to suboptimal solutions. Therefore, we propose a novel approach based on generating a reusable reward function that guides a fast sampling-based motion planner. The proposed method provides improved results in navigation scenarios compared to the former approaches, and it led to about 7% faster autonomous exploration than the decoupled approach. The present results support the suitability of the proposed method in navigation tasks with continuously updated navigation goals.

In this work, we present a reward-driven automated curriculum reinforcement learning approach for interaction-aware self-driving at unsignalized intersections, taking into account the uncertainties associated with surrounding vehicles (SVs). These uncertainties encompass the uncertainty of SVs’ driving intention and also the quantity of SVs. To deal with this problem, the curriculum set is specifically designed to accommodate a progressively increasing number of SVs. By implementing an automated curriculum selection mechanism, the importance weights are rationally allocated across various curricula, thereby facilitating improved sample efficiency and training outcomes. Furthermore, the reward function is meticulously designed to guide the agent towards effective policy exploration. Thus the proposed framework could proactively address the above uncertainties at unsignalized intersections by employing the automated curriculum learning technique that progressively increases task difficulty, and this ensures safe self-driving through effective interaction with SVs. Comparative experiments are conducted in Highway_Env, and the results indicate that our approach achieves the highest task success rate, attains strong robustness to initialization parameters of the curriculum selection module, and exhibits superior adaptability to diverse situational configurations at unsignalized intersections. Furthermore, the effectiveness of the proposed method is validated using the high-fidelity CARLA simulator.

The efficient disassembly of end-of-life electric vehicle batteries(EOL-EVBs) is crucial for green manufacturing and sustainable development. The current pre-programmed disassembly conducted by the Autonomous Mobile Manipulator Robot(AMMR) struggles to meet the disassembly requirements in dynamic environments, complex scenarios, and unstructured processes. In this paper, we propose a Battery Disassembly AMMR(BEAM-1) system based on NeuralSymbolic AI. It detects the environmental state by leveraging a combination of multi-sensors and neural predicates and then translates this information into a quasi-symbolic space. In real-time, it identifies the optimal sequence of action primitives through LLM-heuristic tree search, ensuring high-precision execution of these primitives. Additionally, it employs positional speculative sampling using intuitive networks and achieves the disassembly of various bolt types with a meticulously designed end-effector. Importantly, BEAM-1 is a continuously learning embodied intelligence system capable of subjective reasoning like a human, and possessing intuition. A large number of real scene experiments have proved that it can autonomously perceive, decide, and execute to complete the continuous disassembly of bolts in multiple, multi-category, and complex situations, with a success rate of 98.78%. This research attempts to use NeuroSymbolic AI to give robots real autonomous reasoning, planning, and learning capabilities. BEAM-1 realizes the revolution of battery disassembly. Its framework can be easily ported to any robotic system to realize different application scenarios, which provides a ground-breaking idea for the design and implementation of future embodied intelligent robotic systems.

A necessary capability for humanoid robots is the ability to stand and walk while rejecting natural disturbances. Recent progress has been made using sim-to-real reinforcement learning (RL) to train such locomotion controllers, with approaches differing mainly in their reward functions. However, prior works lack a clear method to systematically test new reward functions and compare controller performance through repeatable experiments. This limits our understanding of the trade-offs between approaches and hinders progress. To address this, we propose a low-cost, quantitative benchmarking method to evaluate and compare the real-world performance of standing and walking (SaW) controllers on metrics like command following, disturbance recovery, and energy efficiency. We also revisit reward function design and construct a minimally constraining reward function to train SaW controllers. We experimentally verify that our benchmarking framework can identify areas for improvement, which can be systematically addressed to enhance the policies. We also compare our new controller to state-of-the-art controllers on the Digit humanoid robot. The results provide clear quantitative trade-offs among the controllers and suggest directions for future improvements to the reward functions and expansion of the benchmarks.