Dibyendu Das

Amir Hossain Raj, Dibyendu Das, Xuesu Xiao

Quadruped robots demonstrate exceptional potential for navigating complex terrain in critical applications such as search and rescue missions and infrastructure inspection However autonomous traversal of confined 3D environments including tunnels caves and collapsed structures remains a significant challenge Existing methods often struggle with rigid gait patterns limited adaptability to diverse geometries and reliance on oversimplified environmental assumptions This paper introduces a Reinforcement Learning RL framework that combines procedural environment generation with policy distillation to enable robust locomotion across various tunnel configurations Our approach leverages a teacher student training paradigm where specialized expert policies trained on procedurally generated tunnel geometries transfer their knowledge to a unified student policy This strategy eliminates the need for complex reward shaping in end-to-end RL training simplifying the process by breaking down complicated tasks into smaller more manageable components that are easier for the robot to learn By synthesizing diverse tunnel structures during training and distilling navigation strategies into a generalizable policy our method achieves consistent traversal across complex spatial constraints where conventional approaches fail We demonstrate through both simulation and real world experiments that our method enables quadruped robots to successfully traverse challenging confined tunnel environments

Dibyendu Das, Sandya Mannarswamy

During early optimization passes, compilers must make predictions for machine-dependent characteristics such as execution unit utilization, number of register spills, latency, throughput etc. to generate better code. Often a hand-written static/analytical hardware cost model is built into the compiler. However, the need for more sophisticated and varied predictions has become more pronounced with the development of deep learning compilers which need to optimize dataflow graphs. Such compilers usually employ a much higher level MLIR form as an IR representation before lowering to traditional LLVM-IR. A static/analytical cost model in such a scenario is cumbersome and error prone as the opcodes represent very high level algebraic/arithmetic operations. Hence, we develop a machine learning-based cost model for high-level MLIR which can predict different target variables of interest such as CPU/GPU/xPU utilization, instructions executed, register usage etc. By considering the incoming MLIR as a text input a la NLP models we can apply well-known techniques from modern NLP research to help predict hardware characteristics more accurately. We expect such precise ML-driven hardware cost models to guide our deep learning compiler in graph level optimizations around operator fusion, local memory allocation, kernel scheduling etc. as well as in many kernel-level optimizations such as loop interchange, LICM and unroll. We report early work-in -progress results of developing such models on high-level MLIR representing dataflow graphs emitted by Pytorch/Tensorflow-like frameworks as well as lower-level dialects like affine. We show that these models can provide reasonably good estimates with low error bounds for various hardware characteristics of interest and can be a go-to mechanism for hardware cost modelling in the future.

Dibyendu Das, Aditya Patankar, Nilanjan Chakraborty et al.

In this paper, we study the problem of methodically obtaining a sufficient set of kinesthetic demonstrations, one at a time, such that a robot can be confident of its ability to perform a complex manipulation task in a given region of its workspace. Although Learning from Demonstrations has been an active area of research, the problems of checking whether a set of demonstrations is sufficient, and systematically seeking additional demonstrations have remained open. We present a novel approach to address these open problems using (i) a screw geometric representation to generate manipulation plans from demonstrations, which makes the sufficiency of a set of demonstrations measurable; (ii) a sampling strategy based on PAC-learning from multi-armed bandit optimization to evaluate the robot's ability to generate manipulation plans in a subregion of its task space; and (iii) a heuristic to seek additional demonstration from areas of weakness. Thus, we present an approach for the robot to incrementally and actively ask for new demonstration examples until the robot can assess with high confidence that it can perform the task successfully. We present experimental results on two example manipulation tasks, namely, pouring and scooping, to illustrate our approach. A short video on the method: https://youtu.be/R-qICICdEos

Dibyendu Das, Alfredo Fontanini, Joshua F. Kogan et al.

Fully optimized automation of behavioral training protocols for lab animals like rodents has long been a coveted goal for researchers. It is an otherwise labor-intensive and time-consuming process that demands close interaction between the animal and the researcher. In this work, we used a data-driven approach to optimize the way rodents are trained in labs. In pursuit of our goal, we looked at data augmentation, a technique that scales well in data-poor environments. Using data augmentation, we built several artificial rodent models, which in turn would be used to build an efficient and automatic trainer. Then we developed a novel similarity metric based on the action probability distribution to measure the behavioral resemblance of our models to that of real rodents.

Sandya Mannarswamy, Dibyendu Das

Instruction combiner (IC) is a critical compiler optimization pass, which replaces a sequence of instructions with an equivalent and optimized instruction sequence at basic block level. There can be thousands of instruction-combining patterns which need to be frequently updated as new coding idioms/applications and novel hardware evolve over time. This results in frequent updates to the IC optimization pass thereby incurring considerable human effort and high software maintenance costs. To mitigate these challenges associated with the traditional IC, we design and implement a Neural Instruction Combiner (NIC) and demonstrate its feasibility by integrating it into the standard LLVM compiler optimization pipeline. NIC leverages neural sequence-to-sequence (Seq2Seq) models for generating optimized encoded IR sequence from the unoptimized encoded IR sequence. To the best of our knowledge, ours is the first work demonstrating the feasibility of a neural instruction combiner built into a full-fledged compiler pipeline. Given the novelty of this task, we built a new dataset for training our NIC neural model. We show that NIC achieves exact match results percentage of 72% for optimized sequences as compared to traditional IC and neural machine translation metric Bleu precision score of 0.94, demonstrating its feasibility in a production compiler pipeline.