This paper proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static obstacles and dense crowds of pedestrians. The policy uses a unique combination of input data to generate the desired steering angle and forward velocity: a short history of lidar data, kinematic data about nearby pedestrians, and a sub-goal point. The policy is trained in a reinforcement learning setting using a reward function that contains a novel term based on velocity obstacles to guide the robot to actively avoid pedestrians and move towards the goal. Through a series of 3D simulated experiments with up to 55 pedestrians, this control policy is able to achieve a better balance between collision avoidance and speed (i.e., higher success rate and faster average speed) than state-of-the-art model-based and learning-based policies, and it also generalizes better to different crowd sizes and unseen environments. An extensive series of hardware experiments demonstrate the ability of this policy to directly work in different real-world environments with different crowd sizes with zero retraining. Furthermore, a series of simulated and hardware experiments show that the control policy also works in highly constrained static environments on a different robot platform without any additional training. Lastly, several important lessons that can be applied to other robot learning systems are summarized. Multimedia demonstrations are available at //www.youtube.com/watch?v=KneELRT8GzU&list=PLouWbAcP4zIvPgaARrV223lf2eiSR-eSS.
相關內容
Magnetic resonance imaging (MRI) is a highly versatile and widely used clinical imaging tool. The content of MRI images is controlled by an acquisition sequence, which coordinates the timing and magnitude of the scanner hardware activations, which shape and coordinate the magnetisation within the body, allowing a coherent signal to be produced. The use of deep reinforcement learning (DRL) to control this process, and determine new and efficient acquisition strategies in MRI, has not been explored. Here, we take a first step into this area, by using DRL to control a virtual MRI scanner, and framing the problem as a game that aims to efficiently reconstruct the shape of an imaging phantom using partially reconstructed magnitude images. Our findings demonstrate that DRL successfully completed two key tasks: inducing the virtual MRI scanner to generate useful signals and interpreting those signals to determine the phantom's shape. This proof-of-concept study highlights the potential of DRL in autonomous MRI data acquisition, shedding light on the suitability of DRL for complex tasks, with limited supervision, and without the need to provide human-readable outputs.
We present a novel method for populating 3D indoor scenes with virtual humans that can navigate the environment and interact with objects in a realistic manner. Existing approaches rely on high-quality training sequences that capture a diverse range of human motions in 3D scenes. However, such motion data is costly, difficult to obtain and can never cover the full range of plausible human-scene interactions in complex indoor environments. To address these challenges, we propose a reinforcement learning-based approach to learn policy networks that predict latent variables of a powerful generative motion model that is trained on a large-scale motion capture dataset (AMASS). For navigating in a 3D environment, we propose a scene-aware policy training scheme with a novel collision avoidance reward function. Combined with the powerful generative motion model, we can synthesize highly diverse human motions navigating 3D indoor scenes, meanwhile effectively avoiding obstacles. For detailed human-object interactions, we carefully curate interaction-aware reward functions by leveraging a marker-based body representation and the signed distance field (SDF) representation of the 3D scene. With a number of important training design schemes, our method can synthesize realistic and diverse human-object interactions (e.g.,~sitting on a chair and then getting up) even for out-of-distribution test scenarios with different object shapes, orientations, starting body positions, and poses. Experimental results demonstrate that our approach outperforms state-of-the-art human-scene interaction synthesis frameworks in terms of both motion naturalness and diversity. Video results are available on the project page: //zkf1997.github.io/DIMOS.
We present a new self-supervised paradigm on point cloud sequence understanding. Inspired by the discriminative and generative self-supervised methods, we design two tasks, namely point cloud sequence based Contrastive Prediction and Reconstruction (CPR), to collaboratively learn more comprehensive spatiotemporal representations. Specifically, dense point cloud segments are first input into an encoder to extract embeddings. All but the last ones are then aggregated by a context-aware autoregressor to make predictions for the last target segment. Towards the goal of modeling multi-granularity structures, local and global contrastive learning are performed between predictions and targets. To further improve the generalization of representations, the predictions are also utilized to reconstruct raw point cloud sequences by a decoder, where point cloud colorization is employed to discriminate against different frames. By combining classic contrast and reconstruction paradigms, it makes the learned representations with both global discrimination and local perception. We conduct experiments on four point cloud sequence benchmarks, and report the results on action recognition and gesture recognition under multiple experimental settings. The performances are comparable with supervised methods and show powerful transferability.
We study the problem of multi-agent coordination in unpredictable and partially observable environments, that is, environments whose future evolution is unknown a priori and that can only be partially observed. We are motivated by the future of autonomy that involves multiple robots coordinating actions in dynamic, unstructured, and partially observable environments to complete complex tasks such as target tracking, environmental mapping, and area monitoring. Such tasks are often modeled as submodular maximization coordination problems due to the information overlap among the robots. We introduce the first submodular coordination algorithm with bandit feedback and bounded tracking regret -- bandit feedback is the robots' ability to compute in hindsight only the effect of their chosen actions, instead of all the alternative actions that they could have chosen instead, due to the partial observability; and tracking regret is the algorithm's suboptimality with respect to the optimal time-varying actions that fully know the future a priori. The bound gracefully degrades with the environments' capacity to change adversarially, quantifying how often the robots should re-select actions to learn to coordinate as if they fully knew the future a priori. The algorithm generalizes the seminal Sequential Greedy algorithm by Fisher et al. to the bandit setting, by leveraging submodularity and algorithms for the problem of tracking the best action. We validate our algorithm in simulated scenarios of multi-target tracking.
Learning provides a powerful tool for vision-based navigation, but the capabilities of learning-based policies are constrained by limited training data. If we could combine data from all available sources, including multiple kinds of robots, we could train more powerful navigation models. In this paper, we study how a general goal-conditioned model for vision-based navigation can be trained on data obtained from many distinct but structurally similar robots, and enable broad generalization across environments and embodiments. We analyze the necessary design decisions for effective data sharing across robots, including the use of temporal context and standardized action spaces, and demonstrate that an omnipolicy trained from heterogeneous datasets outperforms policies trained on any single dataset. We curate 60 hours of navigation trajectories from 6 distinct robots, and deploy the trained GNM on a range of new robots, including an underactuated quadrotor. We find that training on diverse data leads to robustness against degradation in sensing and actuation. Using a pre-trained navigation model with broad generalization capabilities can bootstrap applications on novel robots going forward, and we hope that the GNM represents a step in that direction. For more information on the datasets, code, and videos, please check out our project page //sites.google.com/view/drive-any-robot.
Recently, intermittent computing (IC) has received tremendous attention due to its high potential in perpetual sensing for Internet-of-Things (IoT). By harvesting ambient energy, battery-free devices can perform sensing intermittently without maintenance, thus significantly improving IoT sustainability. To build a practical intermittently-powered sensing system, efficient routing across battery-free devices for data delivery is essential. However, the intermittency of these devices brings new challenges, rendering existing routing protocols inapplicable. In this paper, we propose RICS, the first-of-its-kind routing scheme tailored for intermittently-powered sensing systems. RICS features two major designs, with the goal of achieving low-latency data delivery on a network built with battery-free devices. First, RICS incorporates a fast topology construction protocol for each IC node to establish a path towards the sink node with the least hop count. Second, RICS employs a low-latency message forwarding protocol, which incorporates an efficient synchronization mechanism and a novel technique called pendulum-sync to avoid the time-consuming repeated node synchronization. Our evaluation based on an implementation in OMNeT++ and comprehensive experiments with varying system settings show that RICS can achieve orders of magnitude latency reduction in data delivery compared with the baselines.
Deterministic methods for motion planning guarantee safety amidst uncertainty in obstacle locations by trying to restrict the robot from operating in any possible location that an obstacle could be in. Unfortunately, this can result in overly conservative behavior. Chance-constrained optimization can be applied to improve the performance of motion planning algorithms by allowing for a user-specified amount of bounded constraint violation. However, state-of-the-art methods rely either on moment-based inequalities, which can be overly conservative, or make it difficult to satisfy assumptions about the class of probability distributions used to model uncertainty. To address these challenges, this work proposes a real-time, risk-aware reachability-based motion planning framework called RADIUS. The method first generates a reachable set of parameterized trajectories for the robot offline. At run time, RADIUS computes a closed-form over-approximation of the risk of a collision with an obstacle. This is done without restricting the probability distribution used to model uncertainty to a simple class (e.g., Gaussian). Then, RADIUS performs real-time optimization to construct a trajectory that can be followed by the robot in a manner that is certified to have a risk of collision that is less than or equal to a user-specified threshold. The proposed algorithm is compared to several state-of-the-art chance-constrained and deterministic methods in simulation, and is shown to consistently outperform them in a variety of driving scenarios. A demonstration of the proposed framework on hardware is also provided.
Off-policy evaluation (OPE) is the problem of estimating the value of a target policy using historical data collected under a different logging policy. OPE methods typically assume overlap between the target and logging policy, enabling solutions based on importance weighting and/or imputation. In this work, we approach OPE without assuming either overlap or a well-specified model by considering a strategy based on partial identification under non-parametric assumptions on the conditional mean function, focusing especially on Lipschitz smoothness. Under such smoothness assumptions, we formulate a pair of linear programs whose optimal values upper and lower bound the contributions of the no-overlap region to the off-policy value. We show that these linear programs have a concise closed form solution that can be computed efficiently and that their solutions converge, under the Lipschitz assumption, to the sharp partial identification bounds on the off-policy value. Furthermore, we show that the rate of convergence is minimax optimal, up to log factors. We deploy our methods on two semi-synthetic examples, and obtain informative and valid bounds that are tighter than those possible without smoothness assumptions.
Traditional approaches to the design of multi-agent navigation algorithms consider the environment as a fixed constraint, despite the influence of spatial constraints on agents' performance. Yet hand-designing conducive environment layouts is inefficient and potentially expensive. The goal of this paper is to consider the environment as a decision variable in a system-level optimization problem, where both agent performance and environment cost are incorporated. Towards this end, we propose novel problems of unprioritized and prioritized environment optimization, where the former considers agents unbiasedly and the latter accounts for agent priorities. We show, through formal proofs, under which conditions the environment can change while guaranteeing completeness (i.e., all agents reach goals), and analyze the role of agent priorities in the environment optimization. We proceed to impose real-world constraints on the environment optimization and formulate it mathematically as a constrained stochastic optimization problem. Since the relation between agents, environment and performance is challenging to model, we leverage reinforcement learning to develop a model-free solution and a primal-dual mechanism to handle constraints. Distinct information processing architectures are integrated for various implementation scenarios, including online/offline optimization and discrete/continuous environment. Numerical results corroborate the theory and demonstrate the validity and adaptability of our approach.
We introduce DeepNash, an autonomous agent capable of learning to play the imperfect information game Stratego from scratch, up to a human expert level. Stratego is one of the few iconic board games that Artificial Intelligence (AI) has not yet mastered. This popular game has an enormous game tree on the order of $10^{535}$ nodes, i.e., $10^{175}$ times larger than that of Go. It has the additional complexity of requiring decision-making under imperfect information, similar to Texas hold'em poker, which has a significantly smaller game tree (on the order of $10^{164}$ nodes). Decisions in Stratego are made over a large number of discrete actions with no obvious link between action and outcome. Episodes are long, with often hundreds of moves before a player wins, and situations in Stratego can not easily be broken down into manageably-sized sub-problems as in poker. For these reasons, Stratego has been a grand challenge for the field of AI for decades, and existing AI methods barely reach an amateur level of play. DeepNash uses a game-theoretic, model-free deep reinforcement learning method, without search, that learns to master Stratego via self-play. The Regularised Nash Dynamics (R-NaD) algorithm, a key component of DeepNash, converges to an approximate Nash equilibrium, instead of 'cycling' around it, by directly modifying the underlying multi-agent learning dynamics. DeepNash beats existing state-of-the-art AI methods in Stratego and achieved a yearly (2022) and all-time top-3 rank on the Gravon games platform, competing with human expert players.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191