Robot task planning from high-level instructions is an important step towards deploying fully autonomous robot systems in the service sector. Three key aspects of robot task planning present challenges yet to be resolved simultaneously, namely, (i) factorization of complex tasks specifications into simpler executable subtasks, (ii) understanding of the current task state from raw observations, and (iii) planning and verification of task executions. To address these challenges, we propose LATMOS, an automata-inspired task model that, given observations from correct task executions, is able to factorize the task, while supporting verification and planning operations. LATMOS combines an observation encoder to extract the features from potentially high-dimensional observations with automata theory to learn a sequential model that encapsulates an automaton with symbols in the latent feature space. We conduct extensive evaluations in three task model learning setups: (i) abstract tasks described by logical formulas, (ii) real-world human tasks described by videos and natural language prompts and (iii) a robot task described by image and state observations. The results demonstrate the improved plan generation and verification capabilities of LATMOS across observation modalities and tasks.

This paper focuses on planning robot navigation tasks from natural language specifications. We develop a modular approach, where a large language model (LLM) translates the natural language instructions into a linear temporal logic (LTL) formula with propositions defined by object classes in a semantic occupancy map. The LTL formula and the semantic occupancy map are provided to a motion planning algorithm to generate a collision-free robot path that satisfies the natural language instructions. Our main contribution is LTLCodeGen, a method to translate natural language to syntactically correct LTL using code generation. We demonstrate the complete task planning method in real-world experiments involving human speech to provide navigation instructions to a mobile robot. We also thoroughly evaluate our approach in simulated and real-world experiments in comparison to end-to-end LLM task planning and state-of-the-art LLM-to-LTL translation methods.

Planning and control for high-dimensional robot manipulators in cluttered, dynamic environments require both computational efficiency and robust safety guarantees. Inspired by recent advances in learning configuration-space distance functions (CDFs) as robot body representations, we propose a unified framework for motion planning and control that formulates safety constraints as CDF barriers. A CDF barrier approximates the local free configuration space, substantially reducing the number of collision-checking operations during motion planning. However, learning a CDF barrier with a neural network and relying on online sensor observations introduce uncertainties that must be considered during control synthesis. To address this, we develop a distributionally robust CDF barrier formulation for control that explicitly accounts for modeling errors and sensor noise without assuming a known underlying distribution. Simulations and hardware experiments on a 6-DoF xArm manipulator show that our neural CDF barrier formulation enables efficient planning and robust real-time safe control in cluttered and dynamic environments, relying only on onboard point-cloud observations.

Most multi-agent reinforcement learning (MARL) methods are limited in the scale of problems they can handle. With increasing numbers of agents, the number of training iterations required to find the optimal behaviors increases exponentially due to the exponentially growing joint state and action spaces. This paper tackles this limitation by introducing a scalable MARL method called Distributed multi-Agent Reinforcement Learning with One-hop Neighbors (DARL1N). DARL1N is an off-policy actor-critic method that addresses the curse of dimensionality by restricting information exchanges among the agents to one-hop neighbors when representing value and policy functions. Each agent optimizes its value and policy functions over a one-hop neighborhood, significantly reducing the learning complexity, yet maintaining expressiveness by training with varying neighbor numbers and states. This structure allows us to formulate a distributed learning framework to further speed up the training procedure. Distributed computing systems, however, contain straggler compute nodes, which are slow or unresponsive due to communication bottlenecks, software or hardware problems. To mitigate the detrimental straggler effect, we introduce a novel coded distributed learning architecture, which leverages coding theory to improve the resilience of the learning system to stragglers. Comprehensive experiments show that DARL1N significantly reduces training time without sacrificing policy quality and is scalable as the number of agents increases. Moreover, the coded distributed learning architecture improves training efficiency in the presence of stragglers.

A signed distance function (SDF) is a useful representation for continuous-space geometry and many related operations, including rendering, collision checking, and mesh generation. Hence, reconstructing SDF from image observations accurately and efficiently is a fundamental problem. Recently, neural implicit SDF (SDF-NeRF) techniques, trained using volumetric rendering, have gained a lot of attention. Compared to earlier truncated SDF (TSDF) fusion algorithms that rely on depth maps and voxelize continuous space, SDF-NeRF enables continuous-space SDF reconstruction with better geometric and photometric accuracy. However, the accuracy and convergence speed of scene-level SDF reconstruction require further improvements for many applications. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, several works have focused on improving SDF-NeRF by introducing consistency losses on depth and surface normals between 3DGS and SDF-NeRF. However, loss-level connections alone lead to incremental improvements. We propose a novel neural implicit SDF called "SplatSDF" to fuse 3DGSandSDF-NeRF at an architecture level with significant boosts to geometric and photometric accuracy and convergence speed. Our SplatSDF relies on 3DGS as input only during training, and keeps the same complexity and efficiency as the original SDF-NeRF during inference. Our method outperforms state-of-the-art SDF-NeRF models on geometric and photometric evaluation by the time of submission.

This paper develops a control strategy for pursuit-evasion problems in environments with occlusions. We address the challenge of a mobile pursuer keeping a mobile evader within its field of view (FoV) despite line-of-sight obstructions. The signed distance function (SDF) of the FoV is used to formulate visibility as a control barrier function (CBF) constraint on the pursuer's control inputs. Similarly, obstacle avoidance is formulated as a CBF constraint based on the SDF of the obstacle set. While the visibility and safety CBFs are Lipschitz continuous, they are not differentiable everywhere, necessitating the use of generalized gradients. To achieve non-myopic pursuit, we generate reference control trajectories leading to evader visibility using a sampling-based kinodynamic planner. The pursuer then tracks this reference via convex optimization under the CBF constraints. We validate our approach in CARLA simulations and real-world robot experiments, demonstrating successful visibility maintenance using only onboard sensing, even under severe occlusions and dynamic evader movements.

In this work, we introduce a planning neural operator (PNO) for predicting the value function of a motion planning problem. We recast value function approximation as learning a single operator from the cost function space to the value function space, which is defined by an Eikonal partial differential equation (PDE). Specifically, we recast computing value functions as learning a single operator across continuous function spaces which prove is equivalent to solving an Eikonal PDE. Through this reformulation, our learned PNO is able to generalize to new motion planning problems without retraining. Therefore, our PNO model, despite being trained with a finite number of samples at coarse resolution, inherits the zero-shot super-resolution property of neural operators. We demonstrate accurate value function approximation at 16 times the training resolution on the MovingAI lab's 2D city dataset and compare with state-of-the-art neural value function predictors on 3D scenes from the iGibson building dataset. Lastly, we investigate employing the value function output of PNO as a heuristic function to accelerate motion planning. We show theoretically that the PNO heuristic is $\epsilon$-consistent by introducing an inductive bias layer that guarantees our value functions satisfy the triangle inequality. With our heuristic, we achieve a 30% decrease in nodes visited while obtaining near optimal path lengths on the MovingAI lab 2D city dataset, compared to classical planning methods (A*, RRT*).

This paper presents a novel method for modeling the shape of a continuum robot as a Neural Configuration Euclidean Distance Function (N-CEDF). By learning separate distance fields for each link and combining them through the kinematics chain, the learned N-CEDF provides an accurate and computationally efficient representation of the robot's shape. The key advantage of a distance function representation of a continuum robot is that it enables efficient collision checking for motion planning in dynamic and cluttered environments, even with point-cloud observations. We integrate the N-CEDF into a Model Predictive Path Integral (MPPI) controller to generate safe trajectories. The proposed approach is validated for continuum robots with various links in several simulated environments with static and dynamic obstacles.

This paper develops a real-time decentralized metric-semantic Simultaneous Localization and Mapping (SLAM) approach that leverages a sparse and lightweight object-based representation to enable a heterogeneous robot team to autonomously explore 3D environments featuring indoor, urban, and forested areas without relying on GPS. We use a hierarchical metric-semantic representation of the environment, including high-level sparse semantic maps of object models and low-level voxel maps. We leverage the informativeness and viewpoint invariance of the high-level semantic map to obtain an effective semantics-driven place-recognition algorithm for inter-robot loop closure detection across aerial and ground robots with different sensing modalities. A communication module is designed to track each robot's own observations and those of other robots whenever communication links are available. Such observations are then used to construct a merged map. Our framework enables real-time decentralized operations onboard robots, allowing them to opportunistically leverage communication. We integrate and deploy our proposed framework on three types of aerial and ground robots. Extensive experimental results show an average inter-robot localization error of approximately 20 cm in position and 0.2 degrees in orientation, an object mapping F1 score consistently over 0.9, and a communication packet size of merely 2-3 megabytes per kilometer trajectory with as many as 1,000 landmarks. The project website can be found at https://xurobotics.github.io/slideslam/.

This paper focuses on transferring control policies between robot manipulators with different morphology. While reinforcement learning (RL) methods have shown successful results in robot manipulation tasks, transferring a trained policy from simulation to a real robot or deploying it on a robot with different states, actions, or kinematics is challenging. To achieve cross-embodiment policy transfer, our key insight is to project the state and action spaces of the source and target robots to a common latent space representation. We first introduce encoders and decoders to associate the states and actions of the source robot with a latent space. The encoders, decoders, and a latent space control policy are trained simultaneously using loss functions measuring task performance, latent dynamics consistency, and encoder-decoder ability to reconstruct the original states and actions. To transfer the learned control policy, we only need to train target encoders and decoders that align a new target domain to the latent space. We use generative adversarial training with cycle consistency and latent dynamics losses without access to the task reward or reward tuning in the target domain. We demonstrate sim-to-sim and sim-to-real manipulation policy transfer with source and target robots of different states, actions, and embodiments. The source code is available at \url{https://github.com/ExistentialRobotics/cross_embodiment_transfer}.