Gregory Dudek

Wei-Di Chang, Juan Camilo Gamboa Higuera, Scott Fujimoto et al. · mila

We present an algorithm for Inverse Reinforcement Learning (IRL) from expert state observations only. Our approach decouples reward modelling from policy learning, unlike state-of-the-art adversarial methods which require updating the reward model during policy search and are known to be unstable and difficult to optimize. Our method, IL-flOw, recovers the expert policy by modelling state-state transitions, by generating rewards using deep density estimators trained on the demonstration trajectories, avoiding the instability issues of adversarial methods. We demonstrate that using the state transition log-probability density as a reward signal for forward reinforcement learning translates to matching the trajectory distribution of the expert demonstrations, and experimentally show good recovery of the true reward signal as well as state of the art results for imitation from observation on locomotion and robotic continuous control tasks.

Wei-Di Chang, Scott Fujimoto, David Meger et al. · mila

Imitation Learning from Observation (ILfO) is a setting in which a learner tries to imitate the behavior of an expert, using only observational data and without the direct guidance of demonstrated actions. In this paper, we re-examine optimal transport for IL, in which a reward is generated based on the Wasserstein distance between the state trajectories of the learner and expert. We show that existing methods can be simplified to generate a reward function without requiring learned models or adversarial learning. Unlike many other state-of-the-art methods, our approach can be integrated with any RL algorithm and is amenable to ILfO. We demonstrate the effectiveness of this simple approach on a variety of continuous control tasks and find that it surpasses the state of the art in the IlfO setting, achieving expert-level performance across a range of evaluation domains even when observing only a single expert trajectory without actions.

Fengdi Che, Xiru Zhu, Doina Precup et al.

Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited amount of imperfect expert demonstrations. The algorithm avoids excessive reliance on expert data by relaxing the optimal expert assumption and gradually reducing the usage of uninformative expert data. Experimentally, we evaluate our approach on a sparse-reward chain environment and six more complicated Atari games with delayed rewards. With the proposed methods, we can achieve better results than Deep Q-learning from Demonstrations (Hester et al., 2017) in most environments.

Sahand Rezaei-Shoshtari, Charlotte Morissette, Francois Robert Hogan et al.

In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This work relates to meta RL, contextual RL, and transfer learning, with a particular focus on zero-shot performance at test time, enabled by knowledge of the task parameters (also known as context). Our technical approach is based upon viewing each RL algorithm as a mapping from the MDP specifics to the near-optimal value function and policy and seek to approximate it with a hypernetwork that can generate near-optimal value functions and policies, given the parameters of the MDP. We show that, under certain conditions, this mapping can be considered as a supervised learning problem. We empirically evaluate the effectiveness of our method for zero-shot transfer to new reward and transition dynamics on a series of continuous control tasks from DeepMind Control Suite. Our method demonstrates significant improvements over baselines from multitask and meta RL approaches.

Jikun Kang, Di Wu, Ju Wang et al.

In cellular networks, User Equipment (UE) handoff from one Base Station (BS) to another, giving rise to the load balancing problem among the BSs. To address this problem, BSs can work collaboratively to deliver a smooth migration (or handoff) and satisfy the UEs' service requirements. This paper formulates the load balancing problem as a Markov game and proposes a Robust Multi-agent Attention Actor-Critic (Robust-MA3C) algorithm that can facilitate collaboration among the BSs (i.e., agents). In particular, to solve the Markov game and find a Nash equilibrium policy, we embrace the idea of adopting a nature agent to model the system uncertainty. Moreover, we utilize the self-attention mechanism, which encourages high-performance BSs to assist low-performance BSs. In addition, we consider two types of schemes, which can facilitate load balancing for both active UEs and idle UEs. We carry out extensive evaluations by simulations, and simulation results illustrate that, compared to the state-of-the-art MARL methods, Robust-\ours~scheme can improve the overall performance by up to 45%.

Igor Kozlov, Dmitriy Rivkin, Wei-Di Chang et al.

Radio Access Networks (RANs) for telecommunications represent large agglomerations of interconnected hardware consisting of hundreds of thousands of transmitting devices (cells). Such networks undergo frequent and often heterogeneous changes caused by network operators, who are seeking to tune their system parameters for optimal performance. The effects of such changes are challenging to predict and will become even more so with the adoption of 5G/6G networks. Therefore, RAN monitoring is vital for network operators. We propose a self-supervised learning framework that leverages self-attention and self-distillation for this task. It works by detecting changes in Performance Measurement data, a collection of time-varying metrics which reflect a set of diverse measurements of the network performance at the cell level. Experimental results show that our approach outperforms the state of the art by 4% on a real-world based dataset consisting of about hundred thousands timeseries. It also has the merits of being scalable and generalizable. This allows it to provide deep insight into the specifics of mode of operation changes while relying minimally on expert knowledge.

Yi Tian Xu, Jimmy Li, Di Wu et al.

With the continuous growth in communication network complexity and traffic volume, communication load balancing solutions are receiving increasing attention. Specifically, reinforcement learning (RL)-based methods have shown impressive performance compared with traditional rule-based methods. However, standard RL methods generally require an enormous amount of data to train, and generalize poorly to scenarios that are not encountered during training. We propose a policy reuse framework in which a policy selector chooses the most suitable pre-trained RL policy to execute based on the current traffic condition. Our method hinges on a policy bank composed of policies trained on a diverse set of traffic scenarios. When deploying to an unknown traffic scenario, we select a policy from the policy bank based on the similarity between the previous-day traffic of the current scenario and the traffic observed during training. Experiments demonstrate that this framework can outperform classical and adaptive rule-based methods by a large margin.

Wei-Di Chang, Francois Hogan, Scott Fujimoto et al.

In this paper, we leverage self-supervised vision transformer models and their emergent semantic abilities to improve the generalization abilities of imitation learning policies. We introduce DVK, an imitation learning algorithm that leverages rich pre-trained Visual Transformer patch-level embeddings to obtain better generalization when learning through demonstrations. Our learner sees the world by clustering appearance features into groups associated with semantic concepts, forming stable keypoints that generalize across a wide range of appearance variations and object types. We demonstrate how this representation enables generalized behaviour by evaluating imitation learning across a diverse dataset of object manipulation tasks. To facilitate further study of generalization in Imitation Learning, all of our code for the method and evaluation, as well as the dataset, is made available.

Abhisek Konar, Di Wu, Yi Tian Xu et al.

Communication load balancing aims to balance the load between different available resources, and thus improve the quality of service for network systems. After formulating the load balancing (LB) as a Markov decision process problem, reinforcement learning (RL) has recently proven effective in addressing the LB problem. To leverage the benefits of classical RL for load balancing, however, we need an explicit reward definition. Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward function. In this work, we tackle the communication load balancing problem from an inverse reinforcement learning (IRL) approach. To the best of our knowledge, this is the first time IRL has been successfully applied in the field of communication load balancing. Specifically, first, we infer a reward function from a set of demonstrations, and then learn a reinforcement learning load balancing policy with the inferred reward function. Compared to classical RL-based solution, the proposed solution can be more general and more suitable for real-world scenarios. Experimental evaluations implemented on different simulated traffic scenarios have shown our method to be effective and better than other baselines by a considerable margin.

Jean-François Tremblay, David Meger, Francois Hogan et al.

Robots operating in an open world will encounter novel objects with unknown physical properties, such as mass, friction, or size. These robots will need to sense these properties through interaction prior to performing downstream tasks with the objects. We propose a method that autonomously learns tactile exploration policies by developing a generative world model that is leveraged to 1) estimate the object's physical parameters using a differentiable Bayesian filtering algorithm and 2) develop an exploration policy using an information-gathering model predictive controller. We evaluate our method on three simulated tasks where the goal is to estimate a desired object property (mass, height or toppling height) through physical interaction. We find that our method is able to discover policies that efficiently gather information about the desired property in an intuitive manner. Finally, we validate our method on a real robot system for the height estimation task, where our method is able to successfully learn and execute an information-gathering policy from scratch.

Junliang Luo, Yi Tian Xu, Di Wu et al.

Energy saving in wireless networks is growing in importance due to increasing demand for evolving new-gen cellular networks, environmental and regulatory concerns, and potential energy crises arising from geopolitical tensions. In this work, we propose an approximate dynamic programming (ADP)-based method coupled with online optimization to switch on/off the cells of base stations to reduce network power consumption while maintaining adequate Quality of Service (QoS) metrics. We use a multilayer perceptron (MLP) given each state-action pair to predict the power consumption to approximate the value function in ADP for selecting the action with optimal expected power saved. To save the largest possible power consumption without deteriorating QoS, we include another MLP to predict QoS and a long short-term memory (LSTM) for predicting handovers, incorporated into an online optimization algorithm producing an adaptive QoS threshold for filtering cell switching actions based on the overall QoS history. The performance of the method is evaluated using a practical network simulator with various real-world scenarios with dynamic traffic patterns.

Dmitriy Rivkin, Nikhil Kakodkar, Francois Hogan et al.

This work explores the capacity of large language models (LLMs) to address problems at the intersection of spatial planning and natural language interfaces for navigation. We focus on following complex instructions that are more akin to natural conversation than traditional explicit procedural directives typically seen in robotics. Unlike most prior work where navigation directives are provided as simple imperative commands (e.g., "go to the fridge"), we examine implicit directives obtained through conversational interactions.We leverage the 3D simulator AI2Thor to create household query scenarios at scale, and augment it by adding complex language queries for 40 object types. We demonstrate that a robot using our method CARTIER (Cartographic lAnguage Reasoning Targeted at Instruction Execution for Robots) can parse descriptive language queries up to 42% more reliably than existing LLM-enabled methods by exploiting the ability of LLMs to interpret the user interaction in the context of the objects in the scenario.

Trevor Ablett, Oliver Limoyo, Adam Sigal et al.

Contact-rich tasks continue to present many challenges for robotic manipulation. In this work, we leverage a multimodal visuotactile sensor within the framework of imitation learning (IL) to perform contact-rich tasks that involve relative motion (e.g., slipping and sliding) between the end-effector and the manipulated object. We introduce two algorithmic contributions, tactile force matching and learned mode switching, as complimentary methods for improving IL. Tactile force matching enhances kinesthetic teaching by reading approximate forces during the demonstration and generating an adapted robot trajectory that recreates the recorded forces. Learned mode switching uses IL to couple visual and tactile sensor modes with the learned motion policy, simplifying the transition from reaching to contacting. We perform robotic manipulation experiments on four door-opening tasks with a variety of observation and algorithm configurations to study the utility of multimodal visuotactile sensing and our proposed improvements. Our results show that the inclusion of force matching raises average policy success rates by 62.5%, visuotactile mode switching by 30.3%, and visuotactile data as a policy input by 42.5%, emphasizing the value of see-through tactile sensing for IL, both for data collection to allow force matching, and for policy execution to enable accurate task feedback. Project site: https://papers.starslab.ca/sts-il/

Charlotte Morissette, Amin Abyaneh, Wei-Di Chang et al.

We propose TacFiLM, a lightweight modality-fusion approach that integrates visual-tactile signals into vision-language-action (VLA) models. While recent advances in VLA models have introduced robot policies that are both generalizable and semantically grounded, these models mainly rely on vision-based perception. Vision alone, however, cannot capture the complex interaction dynamics that occur during contact-rich manipulation, including contact forces, surface friction, compliance, and shear. While recent attempts to integrate tactile signals into VLA models often increase complexity through token concatenation or large-scale pretraining, the heavy computational demands of behavioural models necessitate more lightweight fusion strategies. To address these challenges, TacFiLM outlines a post-training finetuning approach that conditions intermediate visual features on pretrained tactile representations using feature-wise linear modulation (FiLM). Experimental results on insertion tasks demonstrate consistent improvements in success rate, direct insertion performance, completion time, and force stability across both in-distribution and out-of-distribution tasks. Together, these results support our method as an effective approach to integrating tactile signals into VLA models, improving contact-rich manipulation behaviours.

Amin Abyaneh, Charlotte Morissette, Mohamad H. Danesh et al.

Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a Stochastic Differential Equation (SDE). However, the same score-based SDE modeling that grants diffusion policies the flexibility to learn diverse behavior also incurs solver and score-matching errors, large data requirements, and inconsistencies in action generation. While less critical in image generation, these inaccuracies compound and lead to failure in continuous control settings. We introduce Contractive Diffusion Policies (CDPs) to induce contractive behavior in the diffusion sampling dynamics. Contraction pulls nearby flows closer to enhance robustness against solver and score-matching errors while reducing unwanted action variance. We develop an in-depth theoretical analysis along with a practical implementation recipe to incorporate CDPs into existing diffusion policy architectures with minimal modification and computational cost. We evaluate CDPs for offline learning by conducting extensive experiments in simulation and real-world settings. Across benchmarks, CDPs often outperform baseline policies, with pronounced benefits under data scarcity.

Wei-Di Chang, Mikael Henaff, Brandon Amos et al.

This paper investigates search in model-based reinforcement learning (RL). Conventional wisdom holds that long-term predictions and compounding errors are the primary obstacles for model-based RL. We challenge this view, showing that search is not a plug-and-play replacement for a learned policy. Surprisingly, we find that search can harm performance even when the model is highly accurate. Instead, we show that mitigating distribution shift matters more than improving model or value function accuracy. Building on this insight, we identify key techniques for enabling effective search, achieving state-of-the-art performance across multiple popular benchmark domains.

Lirong Che, Shuo Wen, Shan Huang et al.

Real-world robotic tasks are long-horizon and often span multiple floors, demanding rich spatial reasoning. However, existing embodied benchmarks are largely confined to single-floor in-house environments, failing to reflect the complexity of real-world tasks. We introduce MANSION, the first language-driven framework for generating building-scale, multi-floor 3D environments. Being aware of vertical structural constraints, MANSION generates realistic, navigable whole-building structures with diverse, human-friendly scenes, enabling the development and evaluation of cross-floor long-horizon tasks. Building on this framework, we release MansionWorld, a dataset of over 1,000 diverse buildings ranging from hospitals to offices, alongside a Task-Semantic Scene Editing Agent that customizes these environments using open-vocabulary commands to meet specific user needs. Benchmarking reveals that state-of-the-art agents degrade sharply in our settings, establishing MANSION as a critical testbed for the next generation of spatial reasoning and planning.

Faraz Lotfi, Khalil Virji, Nicholas Dudek et al.

In this paper, we present an exploration and assessment of employing a centralized deep Q-network (DQN) controller as a substitute for the prevalent use of PID controllers in the context of 6DOF swimming robots. Our primary focus centers on illustrating this transition with the specific case of underwater object tracking. DQN offers advantages such as data efficiency and off-policy learning, while remaining simpler to implement than other reinforcement learning methods. Given the absence of a dynamic model for our robot, we propose an RL agent to control this multi-input-multi-output (MIMO) system, where a centralized controller may offer more robust control than distinct PIDs. Our approach involves initially using classical controllers for safe exploration, then gradually shifting to DQN to take full control of the robot. We divide the underwater tracking task into vision and control modules. We use established methods for vision-based tracking and introduce a centralized DQN controller. By transmitting bounding box data from the vision module to the control module, we enable adaptation to various objects and effortless vision system replacement. Furthermore, dealing with low-dimensional data facilitates cost-effective online learning for the controller. Our experiments, conducted within a Unity-based simulator, validate the effectiveness of a centralized RL agent over separated PID controllers, showcasing the applicability of our framework for training the underwater RL agent and improved performance compared to traditional control methods. The code for both real and simulation implementations is at https://github.com/FARAZLOTFI/underwater-object-tracking.

Yuying Huang, Yiming Yao, Johanna Hansen et al.

This paper presents the portable autonomous probing system (APS), a low-cost robotic design for collecting water quality measurements at targeted depths from an autonomous surface vehicle (ASV). This system fills an important but often overlooked niche in marine sampling by enabling mobile sensor observations throughout the near-surface water column without the need for advanced underwater equipment. We present a probe delivery mechanism built with commercially available components and describe the corresponding open-source simulator and winch controller. Finally, we demonstrate the system in a field deployment and discuss design trade-offs and areas for future improvement. Project details are available on https://johannah.github.io/publication/sample-at-depth our website

Saria Al Laham, Bobak H. Baghi, Pierre-Yves Lajoie et al.

We present a human state estimation framework that allows us to estimate the location, and even the activities, of people in an indoor environment without the requirement that they carry a specific devices with them. To achieve this "device free" localization we use a small number of low-cost Ultra-Wide Band (UWB) sensors distributed across the environment of interest. To achieve high quality estimation from the UWB signals merely reflected of people in the environment, we exploit a deep network that can learn to make inferences. The hardware setup consists of commercial off-the-shelf (COTS) single antenna UWB modules for sensing, paired with Raspberry PI units for computational processing and data transfer. We make use of the channel impulse response (CIR) measurements from the UWB sensors to estimate the human state - comprised of location and activity - in a given area. Additionally, we can also estimate the number of humans that occupy this region of interest. In our approach, first, we pre-process the CIR data which involves meticulous aggregation of measurements and extraction of key statistics. Afterwards, we leverage a convolutional deep neural network to map the CIRs into precise location estimates with sub-30 cm accuracy. Similarly, we achieve accurate human activity recognition and occupancy counting results. We show that we can quickly fine-tune our model for new out-of-distribution users, a process that requires only a few minutes of data and a few epochs of training. Our results show that UWB is a promising solution for adaptable smart-home localization and activity recognition problems.

Shuo Wen, Edwin Meriaux, Mariana Sosa Guzmán et al.

Accurate localization is essential for marine robotics, yet Global Navigation Satellite System (GNSS) signals are unreliable or unavailable even at a very short distance below the water surface. Traditional alternatives, such as inertial navigation, Doppler Velocity Loggers (DVL), SLAM, and acoustic methods, suffer from error accumulation, high computational demands, or infrastructure dependence. In this work, we present a scalable multi-drone GNSS-based tracking system for surface and near-surface marine robots. Our approach combines efficient visual detection, lightweight multi-object tracking, GNSS-based triangulation, and a confidence-weighted Extended Kalman Filter (EKF) to provide stable GNSS estimation in real time. We further introduce a cross-drone tracking ID alignment algorithm that enforces global consistency across views, enabling robust multi-robot tracking with redundant aerial coverage. We validate our system in diversified complex settings to show the scalability and robustness of the proposed algorithm.

Murad Ismayilov, Edwin Meriaux, Shuo Wen et al.

Coordinating multiple autonomous agents in shared environments under decentralized conditions is a long-standing challenge in robotics and artificial intelligence. This work addresses the problem of decentralized goal assignment for multi-agent path planning, where agents independently generate ranked preferences over goals based on structured representations of the environment, including grid visualizations and scenario data. After this reasoning phase, agents exchange their goal rankings, and assignments are determined by a fixed, deterministic conflict-resolution rule (e.g., agent index ordering), without negotiation or iterative coordination. We systematically compare greedy heuristics, optimal assignment, and large language model (LLM)-based agents in fully observable grid-world settings. Our results show that LLM-based agents, when provided with well-designed prompts and relevant quantitative information, can achieve near-optimal makespans and consistently outperform traditional heuristics. These findings underscore the potential of language models for decentralized goal assignment in multi-agent path planning and highlight the importance of information structure in such systems.

Hanna Yurchyk, Wei-Di Chang, Gregory Dudek et al.

We investigate the integration of attention maps from a pre-trained Vision Transformer into voxel representations to enhance bimanual robotic manipulation. Specifically, we extract attention maps from DINOv2, a self-supervised ViT model, and interpret them as pixel-level saliency scores over RGB images. These maps are lifted into a 3D voxel grid, resulting in voxel-level semantic cues that are incorporated into a behavior cloning policy. When integrated into a state-of-the-art voxel-based policy, our attention-guided featurization yields an average absolute improvement of 8.2% and a relative gain of 21.9% across all tasks in the RLBench bimanual benchmark.

Shuo Wen, Edwin Meriaux, Mariana Sosa Guzmán et al.

Accurate localization is crucial for water robotics, yet traditional onboard Global Navigation Satellite System (GNSS) approaches are difficult or ineffective due to signal reflection on the water's surface and its high cost of aquatic GNSS receivers. Existing approaches, such as inertial navigation, Doppler Velocity Loggers (DVL), SLAM, and acoustic-based methods, face challenges like error accumulation and high computational complexity. Therefore, a more efficient and scalable solution remains necessary. This paper proposes an alternative approach that leverages an aerial drone equipped with GNSS localization to track and localize a marine robot once it is near the surface of the water. Our results show that this novel adaptation enables accurate single and multi-robot marine robot localization.

Andrew Holliday, Ahmed El-Geneidy, Gregory Dudek

Planning a network of public transit routes is a challenging optimization problem. Metaheuristic algorithms search through the space of possible transit networks by applying heuristics that randomly alter routes in a network. Existing algorithms almost exclusively use heuristics that modify the network in purely random ways. In this work, we explore whether we can obtain better transit networks using more intelligent heuristics, that modify networks according to a learned preference function instead of at random. We use reinforcement learning to train graph neural nets to act as heuristics. These neural heuristics yield improved results on benchmark synthetic cities with 70 nodes or more, and achieve new state-of-the-art results on the challenging Mumford benchmark. They also improve upon a simulation of the real transit network in the city of Laval, Canada, achieving cost savings of up to 19% over the city's existing transit network.

Faraz Lotfi, Farnoosh Faraji, Nikhil Kakodkar et al.

This paper explores leveraging large language models for map-free off-road navigation using generative AI, reducing the need for traditional data collection and annotation. We propose a method where a robot receives verbal instructions, converted to text through Whisper, and a large language model (LLM) model extracts landmarks, preferred terrains, and crucial adverbs translated into speed settings for constrained navigation. A language-driven semantic segmentation model generates text-based masks for identifying landmarks and terrain types in images. By translating 2D image points to the vehicle's motion plane using camera parameters, an MPC controller can guides the vehicle towards the desired terrain. This approach enhances adaptation to diverse environments and facilitates the use of high-level instructions for navigating complex and challenging terrains.

Andrew Holliday, Gregory Dudek

Planning a public transit network is a challenging optimization problem, but essential in order to realize the benefits of autonomous buses. We propose a novel algorithm for planning networks of routes for autonomous buses. We first train a graph neural net model as a policy for constructing route networks, and then use the policy as one of several mutation operators in a evolutionary algorithm. We evaluate this algorithm on a standard set of benchmarks for transit network design, and find that it outperforms the learned policy alone by up to 20% and a plain evolutionary algorithm approach by up to 53% on realistic benchmark instances.

Oliver Limoyo, Jimmy Li, Dmitriy Rivkin et al.

We introduce PhotoBot, a framework for fully automated photo acquisition based on an interplay between high-level human language guidance and a robot photographer. We propose to communicate photography suggestions to the user via reference images that are selected from a curated gallery. We leverage a visual language model (VLM) and an object detector to characterize the reference images via textual descriptions and then use a large language model (LLM) to retrieve relevant reference images based on a user's language query through text-based reasoning. To correspond the reference image and the observed scene, we exploit pre-trained features from a vision transformer capable of capturing semantic similarity across marked appearance variations. Using these features, we compute suggested pose adjustments for an RGB-D camera by solving a perspective-n-point (PnP) problem. We demonstrate our approach using a manipulator equipped with a wrist camera. Our user studies show that photos taken by PhotoBot are often more aesthetically pleasing than those taken by users themselves, as measured by human feedback. We also show that PhotoBot can generalize to other reference sources such as paintings.

Junliang Luo, Tianyu Li, Di Wu et al.

Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications. In spite of these successes, there exist concerns that limit the wide application of LLMs. A key problem is the problem of hallucination. Hallucination refers to the fact that in addition to correct responses, LLMs can also generate seemingly correct but factually incorrect responses. This report aims to present a comprehensive review of the current literature on both hallucination detection and hallucination mitigation. We hope that this report can serve as a good reference for both engineers and researchers who are interested in LLMs and applying them to real world tasks.

Jimmy Li, Igor Kozlov, Di Wu et al.

The use of learning-based methods for optimizing cellular radio access networks (RAN) has received increasing attention in recent years. This coincides with a rapid increase in the number of cell sites worldwide, driven largely by dramatic growth in cellular network traffic. Training and maintaining learned models that work well across a large number of cell sites has thus become a pertinent problem. This paper proposes a scalable framework for constructing a reinforcement learning policy bank that can perform RAN optimization across a large number of cell sites with varying traffic patterns. Central to our framework is a novel application of anomaly detection techniques to assess the compatibility between sites (tasks) and the policy bank. This allows our framework to intelligently identify when a policy can be reused for a task, and when a new policy needs to be trained and added to the policy bank. Our results show that our approach to compatibility assessment leads to an efficient use of computational resources, by allowing us to construct a performant policy bank without exhaustively training on all tasks, which makes it applicable under real-world constraints.

Oliver Limoyo, Abhisek Konar, Trevor Ablett et al.

We present placing via picking (PvP), a method to autonomously collect real-world demonstrations for a family of placing tasks in which objects must be manipulated to specific, contact-constrained locations. With PvP, we approach the collection of robotic object placement demonstrations by reversing the grasping process and exploiting the inherent symmetry of the pick and place problems. Specifically, we obtain placing demonstrations from a set of grasp sequences of objects initially located at their target placement locations. Our system can collect hundreds of demonstrations in contact-constrained environments without human intervention using two modules: compliant control for grasping and tactile regrasping. We train a policy directly from visual observations through behavioural cloning, using the autonomously-collected demonstrations. By doing so, the policy can generalize to object placement scenarios outside of the training environment without privileged information (e.g., placing a plate picked up from a table). We validate our approach in home robot scenarios that include dishwasher loading and table setting. Our approach yields robotic placing policies that outperform policies trained with kinesthetic teaching, both in terms of success rate and data efficiency, while requiring no human supervision.

Andrew Holliday, Gregory Dudek

In this work we explore the combination of metaheuristics and learned neural network solvers for combinatorial optimization. We do this in the context of the transit network design problem, a uniquely challenging combinatorial optimization problem with real-world importance. We train a neural network policy to perform single-shot planning of individual transit routes, and then incorporate it as one of several sub-heuristics in a modified Bee Colony Optimization (BCO) metaheuristic algorithm. Our experimental results demonstrate that this hybrid algorithm outperforms the learned policy alone by up to 20% and the original BCO algorithm by up to 53% on realistic problem instances. We perform a set of ablations to study the impact of each component of the modified algorithm.

Stefan Wapnick, Travis Manderson, David Meger et al.

We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space which follow trajectories caused by vehicle control actions to enhance predictive accuracy during planning. The attention model is jointly optimized by the task-specific loss and an additional trajectory-constraint loss, allowing adaptability yet encouraging a regularized structure for improved generalization and reliability. Importantly, visual attention is applied in latent feature map space instead of raw image space to promote efficient planning. We validated our model in visual navigation tasks of planning low turbulence, collision-free trajectories in off-road settings and hill climbing with locking differentials in the presence of slippery terrain. Experiments involved randomized procedural generated simulation and real-world environments. We found our method improved generalization and learning efficiency when compared to no-attention and self-attention alternatives.

Morteza Rezanejad, Babak Samari, Elham Karimi et al.

We consider how to directly extract a road map (also known as a topological representation) of an initially-unknown 2-dimensional environment via an online procedure that robustly computes a retraction of its boundaries. In this article, we first present the online construction of a topological map and the implementation of a control law for guiding the robot to the nearest unexplored area, first presented in [1]. The proposed method operates by allowing the robot to localize itself on a partially constructed map, calculate a path to unexplored parts of the environment (frontiers), compute a robust terminating condition when the robot has fully explored the environment, and achieve loop closure detection. The proposed algorithm results in smooth safe paths for the robot's navigation needs. The presented approach is any time algorithm that has the advantage that it allows for the active creation of topological maps from laser scan data, as it is being acquired. We also propose a navigation strategy based on a heuristic where the robot is directed towards nodes in the topological map that open to empty space. We then extend the work in [1] by presenting a topology matching algorithm that leverages the strengths of a particular spectral correspondence method [2], to match the mapped environments generated from our topology-making algorithm. Here, we concentrated on implementing a system that could be used to match the topologies of the mapped environment by using AOF Skeletons. In topology matching between two given maps and their AOF skeletons, we first find correspondences between points on the AOF skeletons of two different environments. We then align the (2D) points of the environments themselves. We also compute a distance measure between two given environments, based on their extracted AOF skeletons and their topology, as the sum of the matching errors between corresponding points.

Bobak H. Baghi, Gregory Dudek

In this paper, we present an algorithm to efficiently learn socially-compliant navigation policies from observations of human trajectories. As mobile robots come to inhabit and traffic social spaces, they must account for social cues and behave in a socially compliant manner. We focus on learning such cues from examples. We describe an inverse reinforcement learning based algorithm which learns from human trajectory observations without knowing their specific actions. We increase the sample-efficiency of our approach over alternative methods by leveraging the notion of a replay buffer (found in many off-policy reinforcement learning methods) to eliminate the additional sample complexity associated with inverse reinforcement learning. We evaluate our method by training agents using publicly available pedestrian motion data sets and compare it to related methods. We show that our approach yields better performance while also decreasing training time and sample complexity.

Sandeep Manjanna, M. Ani Hsieh, Gregory Dudek

This paper presents a distributed scalable multi-robot planning algorithm for informed sampling of quasistatic spatial fields. We address the problem of efficient data collection using multiple autonomous vehicles and consider the effects of communication between multiple robots, acting independently, on the overall sampling performance of the team. We focus on the distributed sampling problem where the robots operate independent of their teammates, but have the ability to communicate their current state to other neighbors within a fixed communication range. Our proposed approach is scalable and adaptive to various environmental scenarios, changing robot team configurations, and runs in real-time, which are important features for many real-world applications. We compare the performance of our proposed algorithm to baseline strategies through simulated experiments that utilize models derived from both synthetic and field deployment data. The results show that our sampling algorithm is efficient even when robots in the team are operating with a limited communication range, thus demonstrating the scalability of our method in sampling large-scale environments.

Sahand Rezaei-Shoshtari, Francois Robert Hogan, Michael Jenkin et al.

Predicting the future interaction of objects when they come into contact with their environment is key for autonomous agents to take intelligent and anticipatory actions. This paper presents a perception framework that fuses visual and tactile feedback to make predictions about the expected motion of objects in dynamic scenes. Visual information captures object properties such as 3D shape and location, while tactile information provides critical cues about interaction forces and resulting object motion when it makes contact with the environment. Utilizing a novel See-Through-your-Skin (STS) sensor that provides high resolution multimodal sensing of contact surfaces, our system captures both the visual appearance and the tactile properties of objects. We interpret the dual stream signals from the sensor using a Multimodal Variational Autoencoder (MVAE), allowing us to capture both modalities of contacting objects and to develop a mapping from visual to tactile interaction and vice-versa. Additionally, the perceptual system can be used to infer the outcome of future physical interactions, which we validate through simulated and real-world experiments in which the resting state of an object is predicted from given initial conditions.

Jean-François Tremblay, Travis Manderson, Aurélio Noca et al.

Dynamics modeling in outdoor and unstructured environments is difficult because different elements in the environment interact with the robot in ways that can be hard to predict. Leveraging multiple sensors to perceive maximal information about the robot's environment is thus crucial when building a model to perform predictions about the robot's dynamics with the goal of doing motion planning. We design a model capable of long-horizon motion predictions, leveraging vision, lidar and proprioception, which is robust to arbitrarily missing modalities at test time. We demonstrate in simulation that our model is able to leverage vision to predict traction changes. We then test our model using a real-world challenging dataset of a robot navigating through a forest, performing predictions in trajectories unseen during training. We try different modality combinations at test time and show that, while our model performs best when all modalities are present, it is still able to perform better than the baseline even when receiving only raw vision input and no proprioception, as well as when only receiving proprioception. Overall, our study demonstrates the importance of leveraging multiple sensors when doing dynamics modeling in outdoor conditions.

Francois Robert Hogan, Michael Jenkin, Sahand Rezaei-Shoshtari et al.

We introduce a new class of vision-based sensor and associated algorithmic processes that combine visual imaging with high-resolution tactile sending, all in a uniform hardware and computational architecture. We demonstrate the sensor's efficacy for both multi-modal object recognition and metrology. Object recognition is typically formulated as an unimodal task, but by combining two sensor modalities we show that we can achieve several significant performance improvements. This sensor, named the See-Through-your-Skin sensor (STS), is designed to provide rich multi-modal sensing of contact surfaces. Inspired by recent developments in optical tactile sensing technology, we address a key missing feature of these sensors: the ability to capture a visual perspective of the region beyond the contact surface. Whereas optical tactile sensors are typically opaque, we present a sensor with a semitransparent skin that has the dual capabilities of acting as a tactile sensor and/or as a visual camera depending on its internal lighting conditions. This paper details the design of the sensor, showcases its dual sensing capabilities, and presents a deep learning architecture that fuses vision and touch. We validate the ability of the sensor to classify household objects, recognize fine textures, and infer their physical properties both through numerical simulations and experiments with a smart countertop prototype.

Travis Manderson, Juan Camilo Gamboa Higuera, Stefan Wapnick et al.

We present Nav2Goal, a data-efficient and end-to-end learning method for goal-conditioned visual navigation. Our technique is used to train a navigation policy that enables a robot to navigate close to sparse geographic waypoints provided by a user without any prior map, all while avoiding obstacles and choosing paths that cover user-informed regions of interest. Our approach is based on recent advances in conditional imitation learning. General-purpose, safe and informative actions are demonstrated by a human expert. The learned policy is subsequently extended to be goal-conditioned by training with hindsight relabelling, guided by the robot's relative localization system, which requires no additional manual annotation. We deployed our method on an underwater vehicle in the open ocean to collect scientifically relevant data of coral reefs, which allowed our robot to operate safely and autonomously, even at very close proximity to the coral. Our field deployments have demonstrated over a kilometer of autonomous visual navigation, where the robot reaches on the order of 40 waypoints, while collecting scientifically relevant data. This is done while travelling within 0.5 m altitude from sensitive corals and exhibiting significant learned agility to overcome turbulent ocean conditions and to actively avoid collisions.

Travis Manderson, Stefan Wapnick, David Meger et al.

We present a method for learning to drive on smooth terrain while simultaneously avoiding collisions in challenging off-road and unstructured outdoor environments using only visual inputs. Our approach applies a hybrid model-based and model-free reinforcement learning method that is entirely self-supervised in labeling terrain roughness and collisions using on-board sensors. Notably, we provide both first-person and overhead aerial image inputs to our model. We find that the fusion of these complementary inputs improves planning foresight and makes the model robust to visual obstructions. Our results show the ability to generalize to environments with plentiful vegetation, various types of rock, and sandy trails. During evaluation, our policy attained 90% smooth terrain traversal and reduced the proportion of rough terrain driven over by 6.1 times compared to a model using only first-person imagery.

Karim Koreitem, Florian Shkurti, Travis Manderson et al.

We consider the task of underwater robot navigation for the purpose of collecting scientifically relevant video data for environmental monitoring. The majority of field robots that currently perform monitoring tasks in unstructured natural environments navigate via path-tracking a pre-specified sequence of waypoints. Although this navigation method is often necessary, it is limiting because the robot does not have a model of what the scientist deems to be relevant visual observations. Thus, the robot can neither visually search for particular types of objects, nor focus its attention on parts of the scene that might be more relevant than the pre-specified waypoints and viewpoints. In this paper we propose a method that enables informed visual navigation via a learned visual similarity operator that guides the robot's visual search towards parts of the scene that look like an exemplar image, which is given by the user as a high-level specification for data collection. We propose and evaluate a weakly supervised video representation learning method that outperforms ImageNet embeddings for similarity tasks in the underwater domain. We also demonstrate the deployment of this similarity operator during informed visual navigation in collaborative environmental monitoring scenarios, in large-scale field trials, where the robot and a human scientist collaboratively search for relevant visual content.

Bharat Joshi, Md Modasshir, Travis Manderson et al.

In this paper, we propose a real-time deep learning approach for determining the 6D relative pose of Autonomous Underwater Vehicles (AUV) from a single image. A team of autonomous robots localizing themselves in a communication-constrained underwater environment is essential for many applications such as underwater exploration, mapping, multi-robot convoying, and other multi-robot tasks. Due to the profound difficulty of collecting ground truth images with accurate 6D poses underwater, this work utilizes rendered images from the Unreal Game Engine simulation for training. An image-to-image translation network is employed to bridge the gap between the rendered and the real images producing synthetic images for training. The proposed method predicts the 6D pose of an AUV from a single image as 2D image keypoints representing 8 corners of the 3D model of the AUV, and then the 6D pose in the camera coordinates is determined using RANSAC-based PnP. Experimental results in real-world underwater environments (swimming pool and ocean) with different cameras demonstrate the robustness and accuracy of the proposed technique in terms of translation error and orientation error over the state-of-the-art methods. The code is publicly available.

Xiru Zhu, Fengdi Che, Tianzi Yang et al.

Despite an impressive performance from the latest GAN for generating hyper-realistic images, GAN discriminators have difficulty evaluating the quality of an individual generated sample. This is because the task of evaluating the quality of a generated image differs from deciding if an image is real or fake. A generated image could be perfect except in a single area but still be detected as fake. Instead, we propose a novel approach for detecting where errors occur within a generated image. By collaging real images with generated images, we compute for each pixel, whether it belongs to the real distribution or generated distribution. Furthermore, we leverage attention to model long-range dependency; this allows detection of errors which are reasonable locally but not holistically. For evaluation, we show that our error detection can act as a quality metric for an individual image, unlike FID and IS. We leverage Improved Wasserstein, BigGAN, and StyleGAN to show a ranking based on our metric correlates impressively with FID scores. Our work opens the door for better understanding of GAN and the ability to select the best samples from a GAN model.

Travis Manderson, Sandeep Manjanna, Gregory Dudek

In this paper we present a cooperative multi-robot strategy to adaptively explore and sample environments that are unfavorable for humans. We propose a methodology for a team of heterogeneous robots to collaborate on information based planning for applications like sampling thermal imagery in a wildfire affected site to assist with detecting spot fires and areas of residual fires, fire mapping and monitoring fire progression or applications in marine domain for coral reef monitoring and survey. We use Gabor filter based texture classifier on aerial images from an Unmanned Aerial Vehicle (UAV) to segment the region of interest into classes. A policy gradient based path planner is used on the texture classified aerial image to plan a path for the Unmanned Ground Vehicle (UGV). The UGV then uses a local planner to reach the goals set by the global planner by avoiding obstacles. The UGV also learns the labels for the segmented classes as drivable and non-drivable using the feedback from the performance while reaching the planned waypoints. We evaluated the building blocks of our approach and present the results with application of these strategies to different domains.

Sandeep Manjanna, Herke van Hoof, Gregory Dudek

Efficient spatial exploration is a key aspect of search and rescue. In this paper, we present a search algorithm that generates efficient trajectories that optimize the rate at which probability mass is covered by a searcher. This should allow an autonomous vehicle find one or more lost targets as rapidly as possible. We do this by performing non-uniform sampling of the search region. The path generated minimizes the expected time to locate the missing target by visiting high probability regions using non-myopic path generation based on reinforcement learning. We model the target probability distribution using a classic mixture of Gaussians model with means and mixture coefficients tuned according to the location and time of sightings of the lost target. Key features of our search algorithm are the ability to employ a very general non-deterministic action model and the ability to generate action plans for any new probability distribution using the parameters learned on other similar looking distributions. One of the key contributions of this paper is the use of non-uniform state aggregation for policy search in the context of robotics.

Melissa Mozifian, Juan Camilo Gamboa Higuera, David Meger et al.

Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of success stories typically use real world data in order to carefully select the DR distribution, or incorporate real world trajectories to better estimate appropriate randomization distributions. In this paper, we consider the problem of finding good domain randomization parameters for simulation, without prior access to data from the target system. We explore the use of gradient-based search methods to learn a domain randomization with the following properties: 1) The trained policy should be successful in environments sampled from the domain randomization distribution 2) The domain randomization distribution should be wide enough so that the experience similar to the target robot system is observed during training, while addressing the practicality of training finite capacity models. These two properties aim to ensure the trajectories encountered in the target system are close to those observed during training, as existing methods in machine learning are better suited for interpolation than extrapolation. We show how adapting the domain randomization distribution while training context-conditioned policies results in improvements on jump-start and asymptotic performance when transferring a learned policy to the target environment.

Johanna Hansen, Sandeep Manjanna, Alberto Quattrini Li et al.

We present a transportable system for ocean observations in which a small autonomous surface vehicle (ASV) adaptively collects spatially diverse samples with aid from a team of inexpensive, passive floating sensors known as drifters. Drifters can provide an increase in spatial coverage at little cost as they are propelled about the survey area by the ambient flow field instead of with actuators. Our iterative planning approach demonstrates how we can use the ASV to strategically deploy drifters into points of the flow field for high expected information gain, while also adaptively sampling the space. In this paper, we examine the performance of this heterogeneous sensing system in simulated flow field experiments.

Johanna Hansen, Kyle Kastner, Aaron Courville et al.

We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obstacles. The combination of high-quality frame generation and classical planning approaches nearly matches true environment performance for our task, demonstrating the usefulness of this method for model-based planning in dynamic environments.

Juan Camilo Gamboa Higuera, David Meger, Gregory Dudek

We present an algorithm for rapidly learning controllers for robotics systems. The algorithm follows the model-based reinforcement learning paradigm, and improves upon existing algorithms; namely Probabilistic learning in Control (PILCO) and a sample-based version of PILCO with neural network dynamics (Deep-PILCO). We propose training a neural network dynamics model using variational dropout with truncated Log-Normal noise. This allows us to obtain a dynamics model with calibrated uncertainty, which can be used to simulate controller executions via rollouts. We also describe set of techniques, inspired by viewing PILCO as a recurrent neural network model, that are crucial to improve the convergence of the method. We test our method on a variety of benchmark tasks, demonstrating data-efficiency that is competitive with PILCO, while being able to optimize complex neural network controllers. Finally, we assess the performance of the algorithm for learning motor controllers for a six legged autonomous underwater vehicle. This demonstrates the potential of the algorithm for scaling up the dimensionality and dataset sizes, in more complex control tasks.