Steven Morad
YOU?
Author Swipe
Language-Conditioned Offline RL for Multi-Robot Navigation Open
We present a method for developing navigation policies for multi-robot teams that interpret and follow natural language instructions. We condition these policies on embeddings from pretrained Large Language Models (LLMs), and train them vi…
View article: CoViS-Net: A Cooperative Visual Spatial Foundation Model for Multi-Robot Applications
CoViS-Net: A Cooperative Visual Spatial Foundation Model for Multi-Robot Applications Open
Autonomous robot operation in unstructured environments is often underpinned by spatial understanding through vision. Systems composed of multiple concurrently operating robots additionally require access to frequent, accurate and reliable…
Generalising Multi-Agent Cooperation through Task-Agnostic Communication Open
Existing communication methods for multi-agent reinforcement learning (MARL) in cooperative multi-robot problems are almost exclusively task-specific, training new communication strategies for each unique task. We address this inefficiency…
Recurrent Reinforcement Learning with Memoroids Open
Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states. Neither model scales particularly well to long sequenc…
Reinforcement Learning with Fast and Forgetful Memory Open
Nearly all real world tasks are inherently partially observable, necessitating the use of memory in Reinforcement Learning (RL). Most model-free approaches summarize the trajectory into a latent Markov state using memory models borrowed fr…
Generalised f-Mean Aggregation for Graph Neural Networks Open
Graph Neural Network (GNN) architectures are defined by their implementations of update and aggregation modules. While many works focus on new ways to parametrise the update modules, the aggregation modules receive comparatively little att…
POPGym: Benchmarking Partially Observable Reinforcement Learning Open
Real world applications of Reinforcement Learning (RL) are often partially observable, thus requiring memory. Despite this, partial observability is still largely ignored by contemporary RL benchmarks and libraries. We introduce Partially …
Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning Open
The problem of permutation-invariant learning over set representations is particularly relevant in the field of multi-agent systems -- a few potential applications include unsupervised training of aggregation functions in graph neural netw…
View article: A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies
A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies Open
GNNs are a paradigm-shifting neural architecture to facilitate the learning of complex multi-agent behaviors. Recent work has demonstrated remarkable performance in tasks such as flocking, multi-agent path planning and cooperative coverage…
Graph Convolutional Memory for Deep Reinforcement Learning. Open
Solving partially-observable Markov decision processes (POMDPs) is critical when applying deep reinforcement learning (DRL) to real-world robotics problems, where agents have an incomplete view of the world. We present graph convolutional …
Graph Convolutional Memory using Topological Priors Open
Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the world. We present graph convolutional memory (GCM), the fi…
Embodied Visual Navigation With Automatic Curriculum Learning in Real Environments Open
We present NavACL, a method of automatic curriculum learning tailored to the navigation task. NavACL is simple to train and efficiently selects relevant tasks using geometric features. In our experiments, deep reinforcement learning agents…
Improving Visual Feature Extraction in Glacial Environments Open
Glacial science could benefit tremendously from autonomous robots, but previous glacial robots have had perception issues in these colorless and featureless environments, specifically with visual feature extraction. This translates to fail…
Building Small-Satellites to Live Through the Kessler Effect Open
The rapid advancement and miniaturization of spacecraft electronics, sensors, actuators, and power systems have resulted in growing proliferation of small-spacecraft. Coupled with this is the growing number of rocket launches, with left-ov…
Building Small-Satellites to Live Through the Kessler Effect Open
The rapid advancement and miniaturization of spacecraft electronics, sensors, actuators, and power systems have resulted in growing proliferation of small-spacecraft. Coupled with this is the growing number of rocket launches, with left-ov…
A Spring Propelled Extreme Environment Robot for Off-World Cave Exploration Open
Pits on the Moon and Mars are intriguing geological formations that have yet to be explored. These geological formations can provide protection from harsh diurnal temperature variations, ionizing radiation, and meteorite impacts. Some have…
Coordination and Control of Multiple Climbing Robots in Transport of Heavy Loads through Extreme Terrain Open
The discovery of ice deposits in the permanently shadowed craters of the lunar North and South Pole Moon presents an important opportunity for In-Situ Resource Utilization. These ice deposits maybe the source for sustaining a lunar base or…
On-Orbit Smart Camera System to Observe Illuminated and Unilluminated Space Objects Open
The wide availability of Commercial Off-The-Shelf (COTS) electronics that can withstand Low Earth Orbit conditions has opened avenue for wide deployment of CubeSats and small-satellites. CubeSats thanks to their low developmental and launc…
Planning and navigation of climbing robots in low-gravity environments Open
Advances in planetary robotics have led to wheeled robots that have beamed back invaluable science data from the surface of the Moon and Mars. However, these large wheeled robots are unable to access rugged environments such as cliffs, can…
Path planning and navigation inside off-world lava tubes and caves Open
Detailed surface images of the Moon and Mars reveal hundreds of cave-like openings. These cave-like openings are theorized to be remnants of lava-tubes and their interior maybe in pristine conditions. These locations may have well preserve…